308 Commits

Include renames

Author	SHA1	Message	Date
3 people	3e76852b04	fix --skip-chat-parsing and --no-prefill-assistant consume the next argument (#2129) ... Co-authored-by: firecoperana <firecoperana>	2026-07-14 12:17:52 +03:00
3 people	b90939934a	model: add openPangu-2.0-Flash (92B-A6B) with MLA-latent cache, DSA/SWA, mHC, and multi-head MTP (#2065) ... * openpangu: Stage-1 converter probe for openPangu-2.0-Flash Add OpenPanguV2ForCausalLM conversion support (converter-only; runtime graph is Stage-2). Registers a new LLM_ARCH_OPENPANGU on the Python/gguf-py side: - gguf-py/constants.py: MODEL_ARCH.OPENPANGU + name, indexer KV keys, 22 new tensor enums (DSA indexer x4, MoME convs x3, param-sink x2, mHC/Hyper- Connections x12, block-post-norm), and the full MODEL_TENSORS list reusing the deepseek MLA + MoE + NextN bricks. - tensor_mapping.py: arch-specific block mappings that disambiguate the sandwich norms (post_attention/pre_mlp/post_mlp) and pin every Pangu-only tensor; non-block global mHC merge module. - convert_hf_to_gguf.py: OpenPanguV2Model (subclasses DeepseekV2Model) with set_gguf_parameters (MLA/MoE/indexer/mHC/param-sink/DSA+SWA metadata), modify_tensors (expert merge, kv_b split, no MTP skip), and the OpenPanguV2Tokenizer pre-tokenizer hash. Validated offline against the real 50-shard safetensors index: all 37,587 tensors map to a GGUF target (0 unmapped), and set_gguf_parameters reads only hparams present in config.json. No weights downloaded; no GPU. Pinned on the ik/dsa_loop_hadamard_blend DSA substrate. * openpangu: Stage-2 arch scaffold (LLM_ARCH_OPENPANGU) — loadable, compiles New arch on main (DSA-decoupled). Declares openPangu-2.0-Flash to the runtime so the model loads into memory; the compute graph is the next step. - llama-arch.{h,cpp}: LLM_ARCH_OPENPANGU + name; 3 KV keys (mhc_num_stream, mhc_recur_norm, param_sink_number); 18 tensor enums (mHC x12, MoME conv x3, param-sink x2, block-post-norm). - llama-model.cpp: OPENPANGU tensor-name block, strings matched to the converter. - llama-model.h: layer + model struct fields (mHC / conv / sink / block-post / merge). - llama-hparams.{h,cpp}: reader (MLA + MoE + sigmoid gate + indexer + mHC + param-sink + NextN); n_layer_kv_from_start = n_layer - nextn (MTP skipped). - llama-load-tensors.cpp: create_openpangu_tensors (GLM-DSA MLA/MoE base + Pangu tensors; indexer loaded-but-unused for dense fallback); dispatch + is_mla_attn. Builds clean (CPU-only libllama). Dense-fallback design: no DSA indexer / SWA windowing / MTP for first generation (exact <=512 tokens). Graph is Stage-2b. * openpangu: fix compresskv_conv dim (kv_lora_rank, not +rope); pin attention order in spec * openpangu: end-to-end runtime — build_openpangu graph runs, generates (garbled) First full forward pass of openPangu-2.0-Flash on ik_llama. Pipeline works end to end: new LLM_ARCH_OPENPANGU loads the Q4 GGUF, the graph executes, and llama-cli generates 40 tokens (EXIT=0). Output is currently garbled (tensor-layout bug to debug), but the structure is proven. graphs/build_openpangu.cpp: dense decompressed-MHA attention + 4-stream mHC (Hyper-Connections) with 20-iter Sinkhorn + MoE(sigmoid+shared) + sandwich norms + entry stream-repeat/tail-merge + inp_out_ids selection. Bring-up fixes to load+run: - llama-vocab.cpp: register 'openpangu' pre-tokenizer (QWEN2 family) - llama.cpp: OPENPANGU -> LLAMA_ROPE_TYPE_NORM (was defaulting to NONE=-1) - llama-load-tensors.cpp: full wkv_b load; k_b/v_b as flattened 2D; block_post_norm dim = S*H (10240); conv weights 2D {3,C}; mHC alpha/beta/gamma + param_sink + merge params use bare (no-.weight) tensor names - llama-model.cpp: OPENPANGU is NOT is_mla_attn (decompressed MHA, standard KV cache) - graph loop bounded to base layers (skip NextN/MTP) v0 deferrals (need conv-state cache / manual attention path, all documented): MoME convs (passthrough), o_conv, param_sink. Next: fix the layout bug to coherence. * openpangu: COHERENT generation — NEOX rope, Sinkhorn orientation, MoME convs, param_sink Four correctness fixes on top of the end-to-end scaffold, verified checkpoint-by- checkpoint against a Python golden reference running on the GGUF's own dequantized weights (block-0 activations now match to rounding at full fidelity): - rope: NORM -> NEOX. Pangu config rope_interleave=false; the Infer source maps it as is_neox_style = not rope_interleave (rotary_mode='half'). - mHC Sinkhorn: the flat h_res block is torch-[r,c] row-major, so a bare ggml reshape lands column-fastest; the doubly-stochastic iteration ran transposed (Sinkhorn is not transpose-symmetric). One transpose at input fixes the whole chain including the mhc_post application. - MoME convs (qa/compresskv/o): were passthrough stubs. Implemented as out = x + causal_conv1d(x) (every Infer call site uses residual_connection=1; tap stats confirm the perturbation form). Taps cast f16->f32 for ggml_mul. Batch-local v0: exact for fresh-sequence prefill; decode steps miss the t-1/t-2 taps until a conv-state cache exists. - param_sink: 128 learned latent-KV entries prepended per layer via a manual attention path (kv_store + explicit soft_max over [sinks ++ cache]); huge effect at short context. o_conv now applied pre-o_proj on the same path. flash_attn forced off for OPENPANGU (FA kernel cannot see the sinks). - converter: add_bos_token=true (HF prepends <|pangu_text_start|> via the post-processor; the key was absent so ik dropped BOS). Greedy Q4_K_M smoke, chat template + <think>: coherent CoT reasoning and a correct answer. Layer-0 instrumentation (opg0_* names) kept for now. * openpangu: MoME conv-state cache — decode steps get real t-1/t-2 taps Allocate a per-layer cache_s_l tensor for OPENPANGU base layers holding the last two pre-conv latents of the three MoME sites, packed [qa 2*1024 | compresskv 2*512 | o 2*6144] f32 (~60KB/layer). The conv helper reads the [C,2] history window (zeros at sequence start, kv_head==0), builds xx = [hist ++ x], and writes the last two columns back each ubatch — the concat naturally handles both prefill chaining and the T==1 shift. Read precedes write in graph order; the fixed-offset copy is graph-reuse safe. Verified: prefill anchors unchanged (bit-path identical, zero-history branch); -ub 1 token-by-token run matches the golden reference at t4 (qlora_conv 0.084, R_block 0.008 rel; attn_out 0.15 on one channel = f16 KV-cache rounding, washes out by post-norm); final logits differ from full-batch only by a common-mode shift that softmax cancels. Chat-template greedy smoke: think-block repetition is gone — clean structured CoT and correct answer. v0 limits documented in the helper: one state slot (single sequence); cache rewinds leave the state stale. * openpangu: NextN/MTP speculative decoding — 1.7-1.8x TG on CPU Wire the three NextN layers (46-48) into ik's MTP speculative framework (--spec-type mtp). v0 drafts with head 1 (layer 46), self-chained by the framework. - llama.cpp: add OPENPANGU to the cparams.mtp arch allowlist (it was silently zeroed, which left the target context without a logits buffer once the server enabled embeddings -> GGML_ASSERT(lctx.logits) in speculative_is_compat). - load-tensors: MTP layers carry no mHC tensors (tail_use_mhc=false in the reference) — create them only for base layers. nextn.* tensors were already wired by the Stage-1 probe. - build_openpangu: extract the attention sublayer into build_openpangu_attention (shared base/MTP); add build_openpangu_mtp: eh_proj(cat(enorm(embed), hnorm(prev_hidden))) -> one plain-residual Pangu block (sandwich norms, convs+param_sink, MoE+shexp, no mHC/block_post_norm) -> shared_head norm+head. MTP branch returns the draft graph when mtp_op_type != NONE; main graph keeps all-token outputs under cparams.mtp. MTP convs run batch-local (no conv-state slot) — affects acceptance only. A/B (Q4_K_M, CPU, greedy, 192-token chat CoT completion, warm back-to-back, medians of 3, bracketed B/A/B): no-spec: 2.44 t/s (2.34-2.86) --spec-type mtp:n_max=3: 4.23 / 4.49 t/s (brackets) => ~1.7-1.8x Draft acceptance 34% on CoT prose (46% on repetitive text); spec and no-spec greedy outputs are byte-identical. Headroom: conv-state for MTP drafts, n_max tuning, true 3-head chaining (spec_step_idx). * server: include draft_n/draft_n_accepted in /completion timings get_formated_timings() (the /completion path) omitted the speculative counters that get_timings() (the OAI path) already reports; add them, guarded by n_draft_total > 0 like the OAI path. * openpangu: position-indexed MoME conv-state ring — rollback-safe spec decoding + MTP draft chaining The v0 single-slot conv state held the last-2 pre-conv latents of the most recent batch, so any speculative draft rejection left latents of REJECTED positions in the state and every later decode ran with wrong t-1/t-2 taps (3 conv sites x 46 layers). At 192-token greedy runs every spec config diverged from no-spec, each differently (rejection-pattern dependent). Replace it with a per-layer ring cache_s_l [n_lora_q+n_lora_kv+n_head*v_dim, 16]: column pos%16 holds position pos's pre-conv latents ([qa|ckv|o] packed). Invariant: reads target only positions before the first batch token, which are committed, and committed latents depend only on the committed prefix - rollback-safe by construction, no checkpointing. Writes cover the last min(T,16) batch positions in <=2 contiguous cpy segments; the copy sources are views of the [hist ++ x] concat so the history read is an ancestor of every write (read-before-write by graph dependency). The ring is also allocated for the NextN/MTP layers, so the draft head chains real conv taps across WARMUP -> sequential DRAFT_GEN steps (was batch-local zero-history per draft token). graph_reuse is forced off for the arch: ring view offsets are position- baked and the reuse patcher only updates the standard K/V-store copies. Measured cost on the CPU server path: none visible. ggml_set_rows driven by an input index tensor is the future reuse-safe shape. Verified (Q4_K_M, CPU, greedy 192-tok chat-CoT, warm single process): - no-spec output byte-identical to pre-ring build - spec output byte-identical to no-spec below the n_predict cap, for all of n_max in {1,2,3,4,6} x p_min in {0,0.3,0.6} (old build: all diverged) - acceptance n3-p0: 33.9% -> 60.9%; n3-p0.3: 58.1% -> 68.9% - TG medians: no-spec 3.19-3.32 t/s; mtp:n_max=3,p_min=0.3 6.97 t/s (~2.1x) * openpangu: DSA lightning indexer + SWA schedule — long-context correctness past the dense fallback The dense fallback was exact only <=512 tokens (SWA window). This wires the real DSA/SWA hybrid schedule, self-contained from GGUF keys the converter already writes (openpangu.swa_layers + sliding_window_list; absent keys keep the old dense fallback): - SWA layers (30 base @512): the generic inp_KQ_mask_swa path, per-layer mask choice in the builder. The NextN/MTP layers are SWA @2048 in the checkpoint schedule; MTP graphs run in their own context, so the mask fill picks hparams.n_swa_mtp when built with an MTP op type. - DSA layers (16, every 3rd): lightning indexer implemented in-graph from the Infer reference semantics (jointfix _pangu_torch_calib): q_idx = wq_b on the post-conv post-norm q-lora latent (24x128), k_idx = rms-normed wk(x) shared across heads, both NEOX-roped on the FIRST n_rot channels; score = sum_g w_g * relu(q_g . k) in f32, causal-masked, exact top-k via argsort + ggml_set_rows scatter into a -1e30 base -> additive selection mask on the existing manual soft_max seam. Selection engages only when the causal window exceeds index_top_k (2048); below that the layer is exactly dense. - Indexer keys cached per position (cache_idx_l, f32 [128, kv_size], DSA layers only) with the same committed-position invariant as the conv-state ring, so speculative rollbacks stay safe. - param sinks remain outside both the window and the selection budget, matching the reference. Verified (Q4_K_M, CPU): - <=512 tokens: byte-identical to the dense build (96/160-token greedy) - indexer scores vs a GGUF-dequant golden reference at 2101 tokens: 1e-3 rel (f16 weight rounding); top-3 selection indices exact on all compared queries - >512 coherence clean; 3.4K-token needle retrieval through active selection (needle outside every SWA window, ~1300 positions pruned) answers exactly * openpangu: MLA-latent KV cache — attention absorbed into the 512-latent, 14x smaller cache, ~2.2x TG Store per position only [ckv_norm 512 | roped k_pe 64] (f32, k_l) plus the transposed 512-latent (f32, v_l, v_trans layout); per-head K/V are never materialized. q_nope is absorbed through attn_k_b (loaded 2D from the converter split for base layers; derived at load via llm_prepare_mla for the NextN layers - now guarded for layers without attention weights, e.g. the idle NextN heads 2/3). The value side is the latent itself, up-projected through attn_v_b after the weighted sum, matching the Infer _forward_dsa reference. param sinks are native latent-space entries, which removes the per-step full-cache concat+cast that dominated long-context decode. llama_state row sizes now come from llama_kv_k_row_embd/llama_kv_v_row_embd (arch-aware), fixing an out-of-bounds crash in the server prompt-cache save path (hparams-derived 9216-wide rows vs actual 576-wide latent rows). Verified (Q4_K_M, CPU): layer-0 attention output matches an f32 golden reference computed from the same GGUF weight encodings (~1e-2 on O(1) values); MTP spec output byte-identical to no-spec; 3.4K needle retrieval through active DSA selection exact under greedy. Output differs from the materialized build at the token level because attn_k_b/attn_v_b are independently quantized tensors - both are legitimate Q4-fidelity encodings. Perf (CPU, warm): no-spec TG 3.2-3.3 -> 6.9-7.1 t/s; mtp:n_max=3,p_min=0.3 -> 11.1 t/s (byte-exact, 67% acceptance); prefill 30.5 t/s at 3.4K; KV self size at 4K ctx: 5.5 GiB -> 391 MiB. Not yet supported on the latent cache: K-shift/defrag (context shifting) - unreached in current usage. * openpangu: fence unsupported serving modes, truth-pass comments, drop dead weight/keys Post-audit hardening. The cache's position-indexed side state (MoME conv ring, DSA indexer keys) made several generic serving paths silently unsound; they are now fenced loudly instead of documented as unsupported: - s_l_position_ring flag on llama_kv_cache: the qnext-state predicate no longer claims the conv ring, so per-seq state save, seq_cp and the s_copy graph skip it - state save/restore refused for the arch at every llama_state_* entry (the ring and idx_l are not in the state format; restoring without them diverges silently) - K-shift/self-extend assert, defrag skips with a warning, server ctx_shift off via new llama_model_supports_ctx_shift() - single sequence enforced at context creation (n_seq_max > 1 refused) - server prompt-cache reuse limited to pure extension via new llama_model_supports_partial_kv_reuse(): mid-cache divergence reprocesses from scratch (the 16-column ring cannot rewind); multi-turn continuation stays fast - MTP draft length clamped to 13 via new llama_model_max_draft_tokens() so a rejected draft can never overwrite the ring columns the next decode reads - K/V cache types forced to f32 for the arch so the KV size log reports the truth - cache_size(): real latent-cache branch (was falling through to the ~14x larger materialized estimate used for offload planning) - unused fused wkv_b no longer loaded (TENSOR_SKIP; the graph runs entirely on the pre-split k_b/v_b), llm_prepare_mla openPangu special-case removed (it was a no-op) - stale v0 comments rewritten to describe the shipped graph; converter stops writing dead keys (dsa_layers, block_post_layernorm_idx) and the tokenizer pre-hash is registered in convert_hf_to_gguf_update.py Gates on this build: greedy spec output byte-identical to no-spec (EOS-terminated, sha-equal); 3.4K needle retrieved exactly; -np 2 / state save / n_max=20 / stale prefix reuse all refused or clamped with clear messages. * openpangu: assert kv_head == first batch position at graph build The ring, indexer and latent stores are addressed by absolute position through kv_head; the fences make append-only decode the only reachable mode, but the invariant was unchecked. Assert it at both graph entries (base and MTP) so any future cache plumbing that breaks it fails at build instead of corrupting output. Worst-case measurement builds pass pos = null and are exempt. * openpangu: cont h_pre before the mHC broadcast mul (CUDA binbcast misreads strided views) h_pre is a row-slice view of the fused mixes tensor. The CPU mul handles the strides; the CUDA broadcast path reads the view as if contiguous, so token 0 mixes correctly and every later token gets h_post/h_res rows instead. First divergent node in the whole graph (oracle rel 0.36 at opg0_attn_mhcpre_x, fixed to 7.5e-5). Sibling views h_post/h_res were already cont-wrapped, which is why only h_pre was exposed. * openpangu: keep DSA zero-trick sources finite (CUDA clamp propagates the 0*(-inf) NaN) The selection-mask base and zeros were built by scaling the MASKED scores by zero, but post-mask sc contains -inf and 0 * -inf = NaN. The CPU clamp launders NaN back to -1e30 (fminf/fmaxf ignore NaN); the CUDA clamp propagates it, so every DSA layer emitted NaN masks at n_kv > top_k and logits collapsed (observed: eval-callback CLAMP sum -1.3e36 on CPU vs nan on CUDA, 11748 NaNs downstream). Scale the pre-mask finite scores instead, which is correct on any backend regardless of clamp NaN semantics. Also defensively cont the strided KQ_mask slice feeding the score add (same strided-view kernel class as the mHC h_pre fix; unproven here but cheap). Gates after fix: 2600-token probe coherent, 3.4K needle exact ('7391') with and without MTP speculation, PP ~120 t/s. * openpangu: f16 latent KV cache option (explicit -ctk/-ctv f16 halves cache memory, f32 stays default) Track explicit cache-type requests through CLI/env; openPangu resolves no-request to f32 (unchanged), accepts explicit f32/f16, warns and falls back to f32 for BF16/quantized. Sink and cached-token KQ paths stay separate until after KQ so the latent cache is read directly without the f32-only concat; value is the sum of the sink and cache matmuls. Ring and DSA indexer caches stay f32; cache_size() follows the resolved types. * openpangu: enable graph reuse * openpangu: wire multi-head MTP drafting * openpangu: add MTP heads override * openpangu: keep MTP update logits last * openpangu: scope MTP warmup heads * speculative: apply per-request MTP heads before warmup * openpangu: fix multi-head MTP warmup computing on unwritten inputs Each chained head called the build_inp_* helpers itself, so the warmup and update graphs held one inp_tokens/inp_pos/inp_out_ids/KQ_mask tensor per head while llama_set_inputs only fills the tensors the lctx pointers reference, i.e. the last head's copies. Every head but the last read unwritten compute-buffer memory: with heads=3 active even head 1's ring, latent cache, and cached one-token draft were computed from garbage, which is why depth-1 acceptance measured 4% against 98% for the heads=1 control. Create the batch inputs once in build_openpangu and pass them to every build_openpangu_mtp call, and fix the two chaining errors that were hiding behind the garbage inputs: - Shift the chained hidden: head k+1's row at position p consumes head k's output row at p-1, the same convention head 1 uses for the target's conditioned hidden rows. The predecessor of a batch's first row lives in the previous warmup/update, carried across decodes through a new inp_mtp_carry input backed by lctx.mtp_carry (written back per ubatch, zeroed when a prompt warmup restarts from position 0). - Fill head 3's cache row at draft step 2: each draft step runs one head, so head 3's own decode at step 3 attended over a never-written row at the step-2 position. Pre-write it from the committed carry. Also include the active head count in the graph-reuse key next to the existing step index (reuse stays forced off for this arch). * speculative: default MTP drafting to a single head A stage without an explicit heads= override previously resolved to 0, meaning all model heads, so multi-head drafting was silently on by default for models that carry more than one NextN layer. Keep it opt-in (heads=N or heads=0 for all) until multi-head measures a win over the single-head config; single-head models are unaffected either way. * speculative: fence MTP head upshift over a warmed prefix Deeper NextN heads only hold valid cache rows for spans that were warmed with them. A request drafting with more MTP heads than the cached prefix was warmed with (e.g. a heads=1 conversation continued with heads=3, a pure extension the divergence fence deliberately allows) would read never-written deeper-head rows: verification keeps the output correct, but acceptance quietly collapses and any measurement taken there is misleading. Track the minimum head count the committed context has been warmed with since position 0 and have the server reprocess from scratch when a request asks for more. Also announce the model's NextN head count and the single-head default once at MTP context setup. * openpangu: skip dead MTP chain compute and stall-free carry readback The update chain's last head and the draft-time row fill only matter for their latent-cache and conv-ring writes; their FFN, norms, and shared head fed nothing. Add a cache-writes-only mode to the MTP block builder that returns after the attention block, and use it at both sites. The multi-head carry readback previously synchronized the scheduler after every warmup/update decode, a hard stall on CUDA. Issue the device-to-host copy async on the backend stream instead (stream order protects the source buffer from later graphs) and synchronize lazily when the host buffer is next consumed or resized. * openpangu: stop emitting fused kv_b tensor * openpangu: default latent cache to f16 * openpangu: refuse unsupported latent cache types * Window OpenPangu SWA cache reads * Gather OpenPangu DSA decode reads Gather DSA decode attention over the selected latent rows for OpenPangu base-model decode and verify graphs. The gathered branch now uses ggml_top_k order directly, runs maskless softmax over sinks plus selected rows for T <= 14, and derives values from the gathered k_l rows instead of the transposed latent cache. * Chunk OpenPangu indexer prefill scoring * Chunk OpenPangu prefill attention * Gather OpenPangu sparse prefill attention * Drop OpenPangu value cache * Add OpenPangu indexer cache type flag * Add OpenPangu q8_0 latent cache type Store the OpenPangu MLA latent K cache as q8_0 via -ctk q8_0 (about 0.53x of f16); the default stays f16 so behavior is unchanged without the flag. Latent V stays f16/f32. The q8 latent cache is a storage format only: it is dequanted to F32 before all compute. K reads go through openpangu_build_k_latent_for_read, V derivation through openpangu_build_v_latent_from_k (full 576-wide row to F32, then slice), and the DSA gather paths already dequant via get_rows. Feeding a q8 latent view directly into the KQ mul_mat corrupts large-context prefill, so that path is removed for quantized caches. The cache write stages ckv and kpe through F32 and writes one full 576-wide q8 row per token. Verified on a small discriminator model: the default f16 path is byte-identical to the prior code; the first-DSA-layer attention envelope is within 0.6% of the f16 cache (linf_rel 0.0057); top-k selection is bit-identical between cache types; the q8 latent cache is 0.531x the f16 size at 8K and 32K context; and generation stays coherent on both the dense and DSA-gather paths at all tested context lengths. * Remove OpenPangu debug trace env knobs and redundant DSA_TOPK override Drop the five LLAMA_OPENPANGU_*_TRACE debug-logging knobs (DSA_GATHER_TRACE, IDX_CHUNK_TRACE, ATT_CHUNK_TRACE, PREFILL_GATHER_TRACE, SWA_WINDOW_TRACE) and the LLAMA_OPENPANGU_DSA_TOPK override, which duplicated the -dsatk / --dsa-top-k CLI flag; top-k now comes solely from cparams.dsa_top_k. The five perf-tuning knobs (DSA_GATHER, IDX_CHUNK, ATT_CHUNK, ATT_KQ_MAX_MIB, PREFILL_GATHER) are retained pending the perf battery. No change to default behavior. * Subchunk OpenPangu DSA prefill gather to fit CUDA grid limit The prefill gathered-attention ggml_get_rows produced dst rows = topk * token_chunk (2048 * 256 = 524288) mapped to the CUDA grid.y dimension, which caps at 65535, crashing with GET_ROWS invalid argument at long context (N_KV around 10.5K with the natural topk of 2048). Split the prefill gather into token subchunks so topk * subchunk_tokens stays within the grid limit, and guard the decode gather with the same fit check (falling back to the dense masked path if a pathological topk would not fit). The subchunking is over the token dimension only, so per-token attention is unchanged and the result is numerically identical. Verified: the GPU sweep runs past the old crash boundary to 22K+ with zero CUDA errors; CPU and -ctk q8_0 paths unaffected. * openpangu: fix scheduler node budget for chunked DSA prefill; drop unused attn_kv_b; remove env tunables - Size the scheduler graph node budget for the chunked DSA prefill so 32K/ub2048 no longer trips the hash-set reservation assert; derive the extra budget from the builder's chunk/top-k/window structure with a fixed safety margin. - Remove LLAMA_OPENPANGU_* environment tunables from both the node-budget estimator and build_openpangu.cpp; use fixed constants in both so they stay in sync. - Converter: emit only the split attn_k_b/attn_v_b projections and drop the unused fused attn_kv_b tensor. * openpangu: restore DeepSeek converter kv_b; drop trace env + dead code; fix dense-fallback node budget - convert_hf_to_gguf.py: restore fused attn_kv_b in DeepseekV2Model (shared parent); openPangu subclass keeps split-only k_b/v_b. Stops newly-converted DeepSeek GGUFs from failing to load. - src/llama.cpp: remove LLAMA_GRAPH_REUSE_TRACE getenv, hit/miss counters, and the unconditional destructor log (no getenv or behavior change for any arch); node-budget estimator now covers the dense-fallback (n_swa==0) attention-chunk loop while skipping absent idx/top-k terms, preserving a strict overcount; remove unreachable openPangu split-cache block. - src/llama-context.h: drop now-dead graph_reuse_hits/misses members. - include/llama.h: move type_k/type_v/idx_type_k *_explicit bools to struct end to avoid a mid-struct ABI shift for out-of-tree consumers. - src/graphs/build_openpangu.cpp: replace vestigial env-struct singletons with the OPENPANGU_* constants; drop a redundant Sinkhorn permute round-trip (one transpose; greedy output verified byte-identical). Decode output unchanged (byte-identical greedy generation verified); shared-file changes are openPangu-gated or restore the pre-PR baseline. * openpangu: chat-parser support (reasoning split + thinking toggle) Two openPangu-only fixes, both gated on the arch-unique token <|pangu_text_start|> so no other model's parsing changes. - chat-diff-analyzer: add a workarounds entry that force-sets TAG_BASED reasoning with an empty start and a </think> end. openPangu prefills <think> in the generation prompt, so the output is delimited only by </think>; the differential detector otherwise learns start="<think>" from the assistant-history form and fails to split, leaking reasoning into content. Same shape as the existing Laguna prefill patch. - chat.cpp: bridge enable_thinking to the template's `thinking` variable. openPangu's template gates reasoning on `thinking` rather than the ecosystem-standard `enable_thinking`, so the standard toggle was inert. An explicit `thinking` chat_template_kwarg still overrides via the extra_context merge. Blast radius: test-chat-auto-parser 437/437 unchanged; the sole test-chat-template diff is a pre-existing GLM trailing-newline. * openpangu: use ggml_cast for latent dequant reads Replace ggml_cpy(view, ggml_new_tensor_2d(F32, ...)) with ggml_cast in the MLA latent V-from-K and K-read helpers. ggml_cast emits the identical GGML_OP_CPY node into a fresh f32 tensor, so behavior is unchanged; it is the idiomatic form. Per review. * openpangu: narrow SWA reuse-key fields to 32-bit The openpangu_swa_window_view reuse key stored n_kv/n_tokens/window/pad as int64_t, but these are bounded well under 2^31 (window/pad are uint32_t at source; n_kv/n_tokens <= context length). Narrow to int32_t/uint32_t and drop the widening casts. w_view/win_off stay int64_t: they feed ggml view dims/offsets. Per review. * openpangu: precompute param_sink derived tensors at load The per-layer attention-sink block (sink_blk [576,NS]) and its transposed latent (s_lat_t [NS,512]) are pure functions of the layer weights, yet were rebuilt every eval across all 49 layers (RMS-norm + cast + concat + transpose). Compute them once at load, mirroring the wk_b derived-weight precompute, and read the stored tensors in build_openpangu_attention. Numerically identical; removes per-token work at decode. * openpangu: replace conv position-ring with ggml_ssm_conv + spec-rollback checkpoint Migrate the MoME depthwise causal conv (three sites per attention sublayer: qa-lora, compressed-kv, attn-out) from the bespoke 16-column position-indexed ring onto the core ggml_ssm_conv op with a recurrent conv-state slot. Cache: s_l becomes [2*conv_col_ne, qnext_state_slots], holding the (d_conv-1)=2 history taps per channel for the three sites (float offsets 0 / 2*n_lora_q / 2*(n_lora_q+n_lora_kv)). Drops the conv_hist_idx / conv_write_idx graph inputs and their fill in llama_set_inputs; adds one single-sequence sq input for ggml_ssm_conv shared across the three sites and the MTP head. Speculative rollback: the position ring self-healed rejected draft columns by absolute position; a recurrent slot does not, since seq_rm is a no-op for recurrent state. openPangu is admitted at the three spec-checkpoint save/init gates so the whole-slot shadow checkpoint (gpu-fallback) snapshots the conv slot before drafting and restores it before the accepted-token replay. The restore path is already keyed on ckpt.valid, so no gate change is needed there. Per-step checkpoint mode is declined for openPangu, which has no SSM recurrent term, so auto mode resolves to the whole-slot shadow. Gated: non-spec needle unchanged; MTP-spec needle correct with healthy draft acceptance (rollback verified via the acceptance canary). * openpangu: single ggml_concat copy for the latent cache store The non-quantized latent store split the [ckv | roped k_pe] row into two views and two cache copies, with a base_offset field on the CacheCopy struct to place the second one. Match the quantized path: concat the two parts and do one copy into the cache row. This drops the second cache-copy slot (OPENPANGU_COPY_K_KPE) and removes base_offset from CacheCopy entirely. Cache contents are unchanged: the concat writes the same [ckv 512 | k_pe 64] bytes to the same row. Gated on the needle for both the f16 latent path (the one that changed) and the q8 latent path, plus coherence. * openpangu: reuse the shared kr_l indexer cache instead of a separate idx_l The DSA lightning indexer stored its per-position keys in an openPangu-only idx_l cache, parallel to the kr_l indexer cache GLM-DSA already uses. Both have the same storage contract: [indexer_head_size, kv_size], idx_type_k dtype, one row per KV cell, written at kv_head and read [dim, n_kv] from zero. openPangu now allocates its indexer keys into kr_l and shares the dsa_cache_copies graph-reuse fixup. The fixup patch is factored into a helper that both the generic path and the openPangu update_cache_copies branch call, so the openPangu indexer copy is repointed to the current kv_head on graph reuse like every other cache write. This drops the idx_l vector, its allocation and memory accounting, and the openPangu third cache-copy slot (now one latent copy per layer). Per-arch allocation predicates stay separate (GLM uses indexer_is_full, openPangu uses the window==0 DSA schedule); only the kr_l storage and the copy fixup are shared. openPangu keeps its no-shift/no-defrag/no-state-I/O behavior, and the GLM Hadamard/k-shift logic stays GLM-gated. Gated: needle correct on f16 and q8 latent caches and under MTP speculation (acceptance unchanged at 0.67), plus coherence. * openpangu: discard pos-0 graphs from reuse; retire stale conv-state comments The ggml_ssm_conv refactor bakes the pos-0 conv-state reset into graph topology (a scale-by-zero node on the state view). A graph built at pos 0 could be reused at pos > 0 when the batch shape and padded n_kv match (a 1-token prompt followed by TG is the concrete case), zeroing the conv history on every reused decode. Admit openPangu at the existing reset_previous gate so pos-0 graphs are discarded from reuse, the same guard the qnext recurrent state relies on. Also retire the internal phase-plan comments the conv refactor left behind: they claimed the spec-checkpoint wiring had not landed in the commit that landed it, and misdescribed the s_l slot as awaiting rollback support. Gated: needle 8457 on f16 and q8 latent, MTP-spec needle (drafts fully accepted), coherence. * openpangu: drop the _explicit cache-type plumbing; validate unconditionally Review follow-up (item 1 of the second review). The explicit/default distinction carried less than claimed: the latent K/V fallback was f16, which is already the -ctk/-ctv and API default, so distinguishing unset from set-to-the-default bought nothing, and the two bools were behaviorally redundant. The only load-bearing use was the indexer cache, where openPangu defaulted to f32 while -ictk defaults to f16. Gating the f16 indexer directly (needle on f16 and q8 latent paths, MTP speculation, coherence) shows no quality difference, so openPangu now takes the standard f16 indexer default and the f32 special case is gone. Default indexer cache memory halves (64 -> 32 MiB at c 8192). Removes type_k_explicit/type_v_explicit/idx_type_k_explicit from llama.h, the cparams/mparams plumbing, and common; the resolve helpers become plain unconditional validators, so -ctk q8_0 is honored and an unsupported type errors out at load instead of silently coercing. Gated: needle 8457 on the new f16-indexer default, on q8 latent with MTP speculation, and with -ictk f32 explicitly honored (64 MiB f32 buffer in the load log); -ctk q4_0 and -ictk q4_1 refused with a clear error. * openpangu: keep MTP draft decodes position-contiguous under speculation The MTP framework's one-token draft shortcut caches a prediction one row past the accepted prefix during the accepted-token update, then skips re-decoding the last sampled token at the next draft round. A mask-addressed cache tolerates the resulting position gap; openPangu's position-addressed append-only cache (cell == position) does not: after a rollback the next draft decode lands one cell behind its position, and after a full acceptance the cache head sits one row ahead of the next draft base, either way tripping the kv_head == pos[0] invariant and aborting the server. The checkpoint admission in the conv refactor made this the standard openPangu speculative flow; the needle-first gates never generated enough draft rounds against a short prompt to reach it. Decline the shortcut re-seed for openPangu in mtp_accept_batch (restoring the drafting behavior all measured acceptance numbers were taken on) and trim rows at or beyond the draft base in mtp_speculative_gen_draft, so every draft decode stays position-contiguous with the cache head. Gated: the crashing flow (short prompt, 512-token spec generation, then a second request) completes with acceptance 0.60 prose / 0.87 code, matching the pre-checkpoint baseline profile; needle 8457 plus coherence on f16+spec and q8+spec. * openpangu: remove stale ring limits and fix MTP graph reuse * cli: preserve speculative carry on fallback Decode an already-emitted pending token when a draft cannot be used instead of sampling unchanged logits and duplicating output. Document single-head MTP as the default and multi-head modes as experimental. --------- Co-authored-by: Joel Farthing <262452229+joelfarthing@users.noreply.github.com>	2026-07-11 12:29:20 +03:00
dmaivelandGitHub	6a909f4ff6	Add --prefetch-experts to stream mmap'd MoE experts into page cache (#2101) ... * Add --prefetch-experts to stream mmap'd MoE experts into page cache * Drop fds, fault experts in with MADV_POPULATE_READ instead of pread * Remove stale note about pread workers * Move MoE prefetch behind ggml_backend_prefetch_* wrappers * Cleanup stale comments * Add --prefetch-experts-threads, drop GGML_MOE_PREFETCH_THREADS env var	2026-07-11 10:43:42 +03:00
KawrakowandGitHub	6d30fa2fe6	Fused indexer top_k (CPU only) (#2098) ... * Indexer topk op - CPU only We do save memory, but it is somehow much slower than what we have on main. * Make it a command line option	2026-07-09 18:04:41 +03:00
Nexes the ElderandGitHub	6198a356a8	Remove deprecated Kompute (Vulkan compute) backend (#2097) ... * Remove broken kompute submodule (ghost - nulled config, corrupted tracking) The kompute submodule at ggml/src/kompute had its .git/modules/kompute/config completely zeroed out (null bytes). The submodule was non-functional and is not used in this fork. Removed: - .gitmodules entry - .git/config [submodule kompute] section - .git/modules/kompute directory - ggml/src/kompute working tree * Extensive removal of all Kompute code and references Removed the entire Kompute Vulkan compute backend which was unmaintained and superseded by the Vulkan backend: Files deleted: - ggml/src/ggml-kompute.cpp (Vulkan compute backend implementation) - ggml/include/ggml-kompute.h (header) - ggml/src/kompute-shaders/ (34 SPIR-V shader source files) Build system: - ggml/CMakeLists.txt: removed GGML_KOMPUTE option - ggml/src/CMakeLists.txt: removed compile_shader function, submodule add, shader compilation, stamp targets, and all KOMPUTE source refs - CMakeLists.txt: removed LLAMA_KOMPUTE deprecation alias Source code: - ggml/src/ggml-backend.cpp: removed kompute reg decl and call - ggml/include/ggml.h: removed ggml_cpu_has_kompute() declaration - ggml/src/ggml.c: removed ggml_cpu_has_kompute() implementation and its reference in ggml_cpu_has_gpublas() - src/llama.cpp: removed #include, backend init, buffer type, model loading guard, and GPU offload check for Kompute - src/llama-model-loader.cpp: removed kompute include - common/common.cpp: removed cpu_has_kompute print - tests/test-c.c: removed kompute include guard - examples/llama-bench/llama-bench.cpp: removed kompute member, construction, field serialization, and display string - scripts/compare-llama-bench.py: removed kompute from key props, bool props, and pretty names - scripts/sync-ggml.sh: removed kompute file copy lines - scripts/sync-ggml-am.sh: removed kompute path mappings Git submodule: - .gitmodules: removed kompute entry - .git/config: removed [submodule kompute] section - .git/modules/kompute: removed - ggml/src/kompute: removed (working tree)	2026-07-08 10:01:01 +02:00
KawrakowandGitHub	a0859ce5ed	GLM-DSA: add ability to use quantized indexer cache (#2075) ... * GLM-DSA: improve TG performance even more * Fix crash when using MTP * GLM-DSA: much better PP performance (CPU-only) * GLM-DSA: allow for quantized indexer cache	2026-07-06 12:04:15 +02:00
5 people	9da563d09d	deepseek2 : GLM-DSA sparse attention (lightning indexer), --dsa off by default (#2045) ... * Add GLM-5.2/DeepSeek-V3.2 DSA lightning indexer (batch-local, single-seq prefill) Implements the sparse top-k "lightning indexer" attention for LLM_ARCH_GLM_DSA in build_deepseek2_layer_attention (ik's deepseek2 graph). What it does (per layer, gated on model.arch==GLM_DSA && indexer_attn_q_b): - indexer_q = indexer_attn_q_b(q_lora latent), split rope(64)/nope(64), NEOX-rope the pe part, concat. indexer_k = indexer_attn_k(attn_norm out), LayerNorm w/ bias, same rope/concat (single key head, MQA). - scores = relu(indexer_k . indexer_q), scaled per-head weights (indexer_proj), summed over heads, + base causal mask, then ggml_top_k(min(top_k, n_tokens)). - sparse mask: ggml_fill(-inf) -> ggml_set_rows(0) at top_k positions -> + causal, used in the soft_max_ext attention path (-mla 1 -fa 0) instead of KQ_mask. Simplifications (intentional, proven sound): - Batch-local: no indexer KV-cache. Indexer keys are the current batch tokens. - Walsh-Hadamard transform omitted: orthonormal rotation, (Hq).(Hk)==q.k, no score change. Validation (GLM-5.2-UD-IQ2_M, 3x P100, -mla 1 -fa 0): - Compiles clean (CUDA sm_60); loads and runs. - c512 -b512 (n_seq=1) PPL = 2.7760, byte-identical to dense baseline (indexer disabled) = 2.7760, all 8 chunks match -> indexer is an exact no-op when top_k>=n_tokens. Proves correctness-preservation. - 3105-token prompt completion (top_k=2048 < 3105 -> indexer ACTIVELY masks): prompt-eval produces coherent, accurate continuation, identical to dense for the prompt+early-gen tokens. No NaN/crash. Confirms the masking path works in prefill. Known limitations (documented follow-ups, NOT handled): - Single-sequence prefill only. Multi-sequence batches (n_seq>1, e.g. perplexity default n_batch>n_ctx) and kv_head>0 (decode) break the batch-local key->slot mapping. n_seq>1 -> NaN (use n_batch==n_ctx). Decode (kv_head>0): each generated token sees only itself as an indexer key, so generation degenerates into repetition after the prompt (dense A/B stays coherent) -- this is the decode-cache stub, the documented next step. - Flash-attn path (-fa 1, F16 mask) still uses dense KQ_mask (soft_max path only). - Decode indexer KV-cache + Hadamard cached-K storage not implemented. Runtime gate: DSA_INDEXER_DISABLE=1 falls back to dense attention (for A/B). Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * GLM-5.2 DSA indexer: decode-correct via persistent indexer-K cache Make the lightning-indexer correct for DECODE (not just prefill). Previously the indexer was batch-local, so a generated token only scored against itself and generation degenerated. Now the indexer keys are cached across the full context. Changes - llama_kv_cache: add per-layer indexer-key cache `kr_l` [indexer_head_size, kv_size] (F16, MQA single head), allocated alongside the MLA latent cache for GLM_DSA. - build_deepseek2_dsa_indexer: write the batch's (Hadamard-rotated) indexer keys to kr_l at kv_head, read back the full [128, n_kv] cached keys, and score the indexer queries against ALL past keys. Returns the full descending argsort of the scores. - Walsh-Hadamard rotation of indexer q/k (cparams.dsa_indexer_hadamard, default on; filled in llama_set_inputs). Score-preserving; improves cached-K F16 precision. - build_deepseek2_dsa_sparse_mask: rank-based full-coverage scatter (write a 0/-BIG penalty into EVERY key slot keyed by rank) instead of partial set_rows into a -inf fill — the CUDA in-place set_rows does not preserve an un-written base, which had corrupted decode when n_kv > top_k. - Attention-sink force-inclusion (DSA_SINK, default 1): boost the first key(s) so the sink always survives top-k. The IQ2_M-quantized indexer under-ranks the sink, and masking it collapsed decode; with the boost, top_k=2048 over n_kv>2048 stays coherent. ggml backend fixes (needed by the indexer) - CUDA argsort: report unsupported when padded ncols > 1024 (one-thread-per-column bitonic launch limit) so the scheduler falls back to the CPU argsort. Fixes "invalid configuration argument" for top_k over a large n_kv. - CUDA cpy/dup: support I32 -> I32 (top_k index copies / cross-backend moves). Validation (GLM-5.2-UD-IQ2_M, 3xP100 + --cpu-moe, -mla 1 -fa 0) - c512 PPL = 2.0743, byte-identical to dense (all 8 chunks): no-op path exact. - Short-context decode (300 tok): coherent, identical to dense. - Long-context decode (2521-tok prompt, n_kv>top_k, real masking of ~474 keys, 120+ tok generated): coherent with the sink boost; dense A/B also coherent. Gated behind arch==GLM_DSA + indexer tensors + kr_l cache; DSA_INDEXER_DISABLE=1 forces dense. Remaining: FA path still uses the dense KQ_mask; multi-sequence (n_seq>1) batches; deepseek32 arch wiring. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * GLM-5.2 DSA indexer: wire sparse mask into the flash-attention path (-fa 1) The DSA sparse top-k mask is now applied on the -fa 1 path (our serving config), not just -fa 0 soft_max. c512 PPL on -fa 1 = 2.0743, byte-identical to dense (no regression, indexer no-op exact at n_kv <= top_k). Gated arch==GLM_DSA with DSA_INDEXER_DISABLE escape; -fa 0 path unchanged. Long-context -fa 1 decode coherence (n_kv > top_k, mask actually biting) validation is still running at commit time; the FA mask reuses the same full-coverage scatter proven coherent on the -fa 0 decode path, so it should hold, but confirm before relying on long-context -fa 1. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * GLM-5.2 DSA indexer: UPDATE 4 — MLA-FA fix merged, FA path validated, multi-seq characterized Document the re-validation after cherry-picking the MLA-FA vec-decode fix (5f18dcc0): - FA path is ALIVE. Long-ctx -fa 1 decode (2521-tok prompt > top_k, mask actively biting) is now COHERENT at -mla 1 and -mla 3, vs the pre-fix degeneration into "0.0.0.0..." repetition. Matches dense (DSA_INDEXER_DISABLE) and -fa 0 controls. - c512 -fa 1 PPL: indexer-ON == dense == 2.0854, byte-identical all 8 chunks (exact no-op when n_kv <= top_k; no regression). The 2.0743->2.0854 shift is the MLA-FA fix changing V accumulation, not an indexer artifact (ON==dense proves it). - Indexer is feature-complete + validated for single-seq prefill+decode on both -fa 0 and -fa 1, at -mla 1 and -mla 3 (the R740 serving target). Remaining PR gaps, characterized honestly: - Multi-seq (n_seq>1) with active mask is BROKEN (n_seq=2 c4096 PPL 62.6 vs dense multi-seq 2.54 and single-seq indexer 3.05). No NaN/crash anymore. Root cause: the indexer uses a single scalar kv_head/n_kv for the whole ubatch; multi-seq needs per-sequence cache writes + per-sequence top-k. Fix deferred (structural). - deepseek32 arch: N/A in this fork. DSA lives entirely under LLM_ARCH_GLM_DSA; there is no LLM_ARCH_DEEPSEEK32 enum. Documented the steps to add one if a real deepseek32 GGUF is ever served. Also commit DSA_REFERENCE.md (verbatim mainline deepseek32/glm-dsa source, the port reference), trimmed of a stray agent-handoff footer. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * GLM-5.2 DSA indexer: per-sequence attention sink — fix multi-seq (n_seq>1) UPDATE 5. The DSA lightning indexer was numerically broken for multi-sequence batches once the top-k mask bites (n_kv > top_k): c4096 n_seq=2 PPL 62.6 vs dense 2.54, while single-seq was fine. Root cause: the attention-sink force-include boosted the GLOBAL key range [0, n_sink) by +1e20, which only protects sequence 0's sink. With several sequences packed contiguously into one ubatch (seq 0 at cells [0,n0), seq 1 at [n0,n1), ...), every non-first sequence's sink lives at cell n0.. (not cell 0), got no boost, and was dropped from top-k once the mask bites — collapsing that sequence (chunk[2]=61.2 while chunk[1]=2.33). The cache write and score/argsort were already per-sequence correct: tokens are placed contiguously like the main K cache, and the base KQ_mask (filled from kv_self.cells[i].has_seq_id) already drives cross-seq keys to -inf before argsort. Only the sink was anchored at the wrong (global) cell. Fix: replace the global arange sink boost with a per-graph input tensor inp_dsa_sink {n_kv, n_tokens} (F32), filled on the CPU in llama_set_inputs from kv_self.cells exactly like the KQ_mask: inp_dsa_sink[j,i] = 1e20 iff cell[i].pos in [0,n_sink) AND cell[i].has_seq_id(seq_of_query_j), else 0 so each query force-includes only its OWN sequence's sink. For a single contiguous sequence from pos 0 this is exactly the old "cell index < n_sink" set with the same magnitude, so n_seq==1 is byte-identical. Validation (3x P100, -ngl 99 --cpu-moe -mla 3 -fa 1, wikitext-2): - c4096 n_seq=2 indexer chunk[2]: 61.2 -> 3.07 (== single-seq 3.05). - c2048 topk=1024 (mask bites): n_seq=4 == n_seq=1 chunk-for-chunk (2.5005/2.6080/2.7759/3.1137 vs .../3.1138) -> multi-seq is numerically identical to processing each sequence alone. - c512 n_seq=1 indexer ON == dense, all 4 chunks byte-identical (no regression). n_seq=4 at full c4096 (n_kv=16384) OOMs the P100 compute buffer (capacity, not correctness; n_seq=4 proven correct at c2048/n_kv=8192). GLM-5.2 DSA indexer is now sequence-correct for n_seq>=1, prefill+decode, soft_max+FA, -mla 1/-mla 3. Fully general and PR-ready. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * GLM-5.2 DSA indexer: UPDATE 6 — serving-correctness (kr_l maintained across shift/defrag/seq-ops; per-seq sink on first-present pos) An adversarial review found the indexer was proven on the perplexity path but not the serving path: the persistent indexer-K cache kr_l was written/read but never *maintained* by the KV-cache mutators, and the attention sink anchored on absolute pos<n_sink (wrong after multi-turn seq_rm). This closes those gaps and pins down what is actually reachable on the MLA model. kr_l maintenance: - build_k_shift (llama-build-context.cpp): rotate the indexer keys by the same per-cell delta as the main K. The cached key is H*concat(RoPE(k_pe,pos),k_nope), so un-Hadamard (H sym/orthonormal => H*H=I) -> RoPE-delta the pe sub-block -> re-Hadamard. Exact because GLM-DSA has no rope-scaling metadata (ext_factor=0, attn_factor=1, freq_scale=1), so NEOX RoPE is pure/composable. Params mirror the forward indexer RoPE exactly (rope_factors=nullptr); no DEEPSEEK2 yarn-shift leak. Non-in-place (cont->rope->concat->re-Had->cpy), no aliasing. K-shift Hadamard input filled in llama_set_k_shift with the identical Sylvester construction. - build_defrag: kr_l row-move mirrors the k_l move (defrag never changes pos, so no re-RoPE). max_moves divisor 6->9 *n_layer when the indexer cache is present. - seq_rm/seq_cp/seq_keep are metadata-only (verified) so kr_l rows stay matched to cells; seq_add/seq_div set has_shift and route through K-shift. No seq-op change. Per-seq sink (llama.cpp llama_set_inputs): anchor on each sequence's FIRST PRESENT pos (min present pos over the scored n_kv span), not absolute pos<n_sink. After multi-turn seq_rm drops a sequence's early tokens its earliest survivor has pos>=n_sink; the absolute test would protect nothing. Fresh seq at pos 0 => min=0 => byte-identical to the old behaviour. Serving-shift finding (the whole point): a RoPE context-shift on this model is REFUSED BY THE ENGINE. get_can_shift() returns false for all MLA models (is_mla_model() includes GLM_DSA); llama_kv_cache_update returns 1 -> "main : failed to eval". Reproduced AND isolated with a dense control (DSA_INDEXER_DISABLE=1): dense fails identically at the same token. The failure is pre-existing MLA engine behaviour, independent of the indexer. On the MLA path the shift never happens, so the indexer's kr_l can never desync via K-shift; the build_k_shift kr_l block is correct-and-dormant (documented loudly in code). Validation (3x P100, -ngl 99 --cpu-moe -mla 3 -fa 1, GGML_CUDA_NO_PINNED=1, numactl --interleave=all, wikitext-2): - No regression: c512 n_seq=1 indexer ON == dense == 2.1957 +/- 0.12031, byte-identical all 4 chunks (2.2770/2.8741/2.3956/2.1957). - Multi-seq: c4096 n_seq=2 chunk[1]=2.33 chunk[2]=3.07 healthy (== UPDATE 5; per-seq sink change did not regress). - Serving shift: engine-refused for MLA, dense control fails identically. - Independent adversarial review: GO, no correctness defect in the diff. - Build clean (llama-cli, llama-perplexity, sm_60). Comments updated (build_deepseek2.cpp): multi-seq+FA no longer limitations; sink description matches per-seq min-pos anchoring; BIG=1e30 masks on both soft_max and FA paths. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * GLM-5.2 DSA indexer: UPDATE 7 — FIX latent graph-reuse cache-fixup omission for the kr_l indexer cache update_cache_copies() re-points the K/V cache writes to the current kv_head whenever a compute graph is REUSED (can_reuse_graph reuses iff kv_self.n == prev->n_kv). The persistent indexer-key cache write (kr_l) is a separate ggml_cpy whose destination view bakes kv_head at graph-build time, and it was NEVER registered for that fixup. Under FA the cache pads to 256, so consecutive single-token decode ubatches share the same padded n_kv and the graph IS reused; without the fixup the kr_l write keeps landing in the first ubatch's slot and later ubatches never populate their own recent index-key cells (those cells stay at the alloc-zeroed 0.0). Structurally identical to the MiniMax MSA bug (fork commit 133d14c9). Fix (mirrors the K/V cache_copies fixup, same shape as MSA 133d14c9): - llama-context.h: new std::vector<CacheCopy> dsa_cache_copies. - llama.cpp ctor: resize dsa_cache_copies to n_layer (null entries -> no-op when DSA off). - build_deepseek2.cpp: register the kr_l ggml_cpy as dsa_cache_copies[il] = {kr_cpy, kr->nb[1]}. - llama.cpp update_cache_copies(): re-point each registered cpy view_offs = kv_head*step and patch src[1]->data/data, exactly like K/V, with the c.cpy->view_src == kv_self.kr_l[il] (+ null/op) guard the MSA fix omitted. soft_max / non-DSA paths byte-identical. Validation (GLM-5.2-UD-IQ2_M, 3x P100 -ngl 99 --cpu-moe -t 32, NO_PINNED, P2P-disable patch re-applied to get a working multi-GPU baseline — see UPDATE 7.3; that patch was lost in the upstream rebase and is required separately): - c512 -fa1 -mla3 indexer ON: 2.1983 (== prior baseline; build healthy). - Long-ctx FA decode, 2735-tok recall prompt, -mla3 -fa1 temp0, reuse ON (default): coherent, correct deep-context recall ("Dr. Mariana Velasquez ... Daniel Okonkwo") on BOTH the fixed and the unfixed binary. - ub128 PPL -fa1 -mla3 reuse ON, unfixed: 1.7239/1.8211/2.1888/2.4517, healthy (no inflation). Honest scope: the bug is real in code but LATENT for GLM-DSA at its configured top_k=2048 (permissive selection keeps the genuinely-attended recent blocks even when reuse leaves some recent index-key cells stale), unlike MSA's tighter top-k where it inflated PPL ~2x. The fix is correct and prevents the latent corruption from biting at any tighter top_k / longer ctx / future serving config. The pre-P2P-patch "nan" seen at ub128 was P2P corruption, not this bug. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * GLM-DSA: convert sparse-attention control from env vars to CLI args (off by default) Implements ikawrakow's direction from discussion #2040: the DSA sparse indexer must be controllable via command-line argument (not environment variables), and must be OFF by default for now. Control surface, before -> after: DSA_INDEXER_DISABLE (env, inverted: on-by-default) -> --dsa / -dsa (cparams.dsa, default false; opt-in, dense-by-default) DSA_TOPK_OVERRIDE (env) -> --dsa-top-k N / -dsatk N (cparams.dsa_top_k, default -1 == model's configured indexer_top_k) DSA_HADAMARD_DISABLE, DSA_SINK (env) -> kept as DEBUG-ONLY env knobs (clearly commented; no CLI surface, not system on/off controls) Plumbing mirrors existing boolean/int feature flags (-mla, -khad): include/llama.h llama_context_params {bool dsa; int dsa_top_k;} src/llama.cpp default_params (false / -1); cparams assignment src/llama-cparams.h llama_cparams {bool dsa=false; int dsa_top_k=-1;} common/common.h gpt_params {bool dsa=false; int dsa_top_k=-1;} common/common.cpp arg parse + help text + cparams copy src/graphs/build_deepseek2.cpp gate now checks cparams.dsa instead of getenv; top-k override reads cparams.dsa_top_k. Stays arch-gated to LLM_ARCH_GLM_DSA. When --dsa is off (default) the indexer function is never called -> existing dense MLA path, byte-identical to no-feature. Validation (GLM-5.2-UD-IQ2_M, 3x P100, -ngl 99 --cpu-moe -mla 3 -fa 1, wikitext-2, 4 chunks @ c2560): --dsa OFF (default, dense): PPL 2.4151 (graph nodes 4166) --dsa ON, default top_k=2048: PPL 2.4697 (graph nodes 8846) --dsa ON, --dsa-top-k 1024: PPL 3.5107 Off-by-default runs the dense path; ON activates the indexer (node count jumps, PPL shifts as the top-k mask bites once n_kv > top_k). No env var is consulted for the primary on/off or the top-k knob. Graph-parallel (-sm graph) interaction (the item ikawrakow flagged): Under -sm graph the MLA layers are TP-split (wo->extra) and route to build_deepseek2_tp_attention(), which contains NO indexer code. So --dsa is silently a NO-OP under -sm graph: it does not error or crash, it runs dense. Empirically, --dsa --dsa-top-k 1024 under -sm graph gives PPL 2.4308 (chunks 1.6967/1.7906/2.1664/2.4308) -- the dense baseline (2.4151), NOT the DSA top_k=1024 numbers (3.5107). The 0.016 delta is f16 TP-reduce numerics, not DSA. Conclusion: DSA "works under deepseek2" only on the non-TP (layer) path; serving DSA with -sm graph would require wiring the indexer into the TP attention path (or a dedicated DSA arch). Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * GLM-DSA: warn that --dsa is inactive under -sm graph/attn (TP path runs dense MLA) The DSA lightning indexer is built only in the layer-mode (non-TP) attention path. Under -sm graph / -sm attn the tensor-parallel attention path has no indexer, so --dsa would silently run dense MLA. Emit a clear one-time LLAMA_LOG_WARN at context creation instead of degrading silently. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * GLM-DSA: drop in-tree dev reference docs from the PR branch DSA_REFERENCE.md and the R740 progress note are development scratch, not part of the submission. Remove them so the PR diff is code-only. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * GLM-DSA: fix CPU-only crashes in the sparse-attention path PR #2045 adds GLM-DSA sparse attention but was validated on CUDA (--cpu-moe). A CPU-only build (-ngl 0 --dsa) crashes in four spots where the CUDA backend tolerates something the CPU backend does not. These make GLM-5.2 --dsa run coherently on CPU; with --dsa off they are no-ops (DSA CPU path only). 1. set_rows into an F32 dest segfaults (ggml.c set_rows_f32): type_traits[F32].from_float is NULL, so the DSA sparse-mask scatter calls a NULL fn (segfault at ip=0). memcpy when the dest is F32. CUDA has a real F32 set_rows path, so this only bit the CPU build. 2. ggml_add(F32 score, F16 mask) aborts on CPU (build_deepseek2_dsa_indexer and build_deepseek2_dsa_sparse_mask): under -fa 1 the dense KQ_mask is F16 and CPU add only accepts F32+F16 when src0 is F16. Cast the causal mask view to F32. CUDA's add accepts the mixed types. 3. dsa_fa_mask dim-1 concat must be F32 on CPU (build_deepseek2_dsa_fa_mask): CPU ggml_concat only supports F16 along dim 0; do the row (dim-1) concat in F32 then cast the result to F16. CUDA supports the F16 dim-1 concat. 4. indexer k_norm epsilon is 0 -> ggml_norm aborts (llama-hparams.cpp): the lightning-indexer k_norm is a non-RMS LayerNorm using f_norm_eps, but the GLM-DSA GGUF only carries the RMS eps so f_norm_eps stays 0 (GGML_ASSERT(eps > 0)). Mirror the RMS eps. CUDA's norm doesn't assert on eps=0. Validated: GLM-5.2 UD-Q4_K_M, single-socket Xeon w7-2475X, CPU-only (-ngl 0 --dsa) - coherent at 49K+ ctx, correct 30K needle retrieval, prefill flat with length (~32 tok/s, the O(L) DSA signature) vs the dense build's O(L^2) decline. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * DSA: loop over attention heads + use builtin Hadamard * DSA: ggml_blend * DSA: remove a bunch of unnecessary ggml_cont * DSA: fix CUDA blend - but something is still wrong * DSA: use ggml_top_k instead of ggml_argsort when FA is ON * CUDA: add CUB based argsort * DSA: avoid graph leaves * Various * GLM-5.2 DSA: IndexShare (shared layers reuse full-layer top-k) GLM-5.2's indexer_types marks 21 'full' layers that compute their own lightning-indexer top-k and 57 'shared' layers that reuse the previous full layer's top-k. This port computed an independent top-k on every layer, which mis-selects keys on the 57 shared layers (the transformers reference sets indexer=None on shared layers and reuses prev_topk). Shared layers now reuse the most-recent full layer's selection. Full/ shared map derived from the config rule (full iff il<=1 or il%4==2), which reproduces indexer_types exactly; loader can later override from GGUF metadata. Built on #2063's tree; head-loop/ggml_hadamard/ggml_blend/ argsort/FA-mask unchanged. 4K PPL (unsloth IQ2_M, top_k 2048, CPU): DSA-on 3.1922 -> 2.7111, dense 2.6972 (~97% of the gap). top_k>=n_kv reproduces dense exactly. Single- seq and 4x8 parallel decode coherent. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * Apply suggestion from @ikawrakow --------- Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com> Co-authored-by: mgkwill <168222+mgkwill@users.noreply.github.com> Co-authored-by: Kawrakow <iwankawrakow@gmail.com>	2026-07-02 09:36:49 +02:00
FarmadupeandGitHub	af62a37acd	Prune examples/llava. Dead code. (#2025) ... examples/llava has been replaced by mtmd since late 2025, and has been out-of-build in ik_llama.cpp since examples/CMakeLists.txt removed it in #798. Repointed descriptions from llava to mtmd where they remained.	2026-06-26 08:48:48 +02:00
3 people	befbc0945b	server: variance based checkpoint eviction (#2020) ... Co-authored-by: firecoperana <firecoperana>	2026-06-24 08:54:07 +02:00
SamuelOliveirads	3a1d46c4d1	Merge remote-tracking branch 'origin/main' into feat/dflash-implementation ... # Conflicts: # common/common.cpp # common/speculative.cpp # convert_hf_to_gguf.py # examples/server/server-context.cpp # examples/server/server-context.h # src/llama-arch.cpp # src/llama-arch.h # src/llama-model.cpp # src/llama.cpp	2026-06-13 17:27:52 -03:00
Samuel Oliveira AlvesandGitHub	8a38025174	Refactor: Move spec outside server (#1949) ... * Refactor speculative decoding: move logic outside of server * remove duplicated tokens in mtp kv cache * narrow to only discard draft cells in MTP * revert mtp_speculative_gen_draft	2026-06-12 18:12:39 +02:00
KawrakowandGitHub	366e478cb6	Bug fixes (#1940) ... * Bug fixes * More	2026-06-10 07:45:49 +02:00
FarmadupeandGitHub	6b9de3dbaa	Fix mrope application across chunk boundaries (Fixes #993 and #1902 -- part 2) (#1918) ... * (qwen3vl) Correct calculation for injection point of deepstack image embeddings INjection point for deepstack embeddings used Hyperparameter n_embd_inp(), which caused the hidden state to be double accounted for, causing an OOB array access. The correct accessor is n_embd() * Fix m-rope when pipeline parallelism is enabled	2026-06-05 17:10:02 +02:00
Samuel Oliveira AlvesandGitHub	007d640098	Standardize speculative decoding arguments on the server (#1908) ... * refactor spec args * add shell-safe quoting of string-valued stage keys in speculative decoding	2026-06-04 15:44:57 +02:00
3 people	6c0180d702	server: enable mcp proxy (#1904) ... * update http lib * Add cors proxy --------- Co-authored-by: firecoperana <firecoperana>	2026-06-04 15:43:07 +02:00
KawrakowandGitHub	8960c5ba5e	Add extra nodes when dealing with MLA and amb (#1899)	2026-05-29 15:17:24 +03:00
SamuelOliveirads	82cff238fe	Initial dflash implementation	2026-05-28 18:57:58 -03:00
KawrakowandGitHub	b4e1d916c5	Per GPU fit margin (#1872)	2026-05-25 08:16:45 +03:00
dungquixote42andGitHub	642c038ccd	Extend expiring logit bias to other sampling parameters (#1770) ... * initial commit * fix underflow bug, add debug prints, update macro/variable names * fix phrases-sharing-1-flag bug, replace macros with struct member function * cleanup * fix file parsing * string_split_open_close() -> string_extract(), improve escape handling * support multiple nested entries * make persistent entries global, simplify file parsing * cosmetic changes * add support for jumping to exitword * update variable names * fix bad search bug * better debug prints, reorg * replace lambda with string_is_found(), add string_unescape() for debug * add support for inline comments * add missing debug print macro * fix type promotion bug * actually fix type promotion bug	2026-05-23 19:19:12 +03:00
3 people	c07a052315	MLA tensor parallelism under -sm graph (DEEPSEEK2/GLM_DSA/MISTRAL4) (#1821) ... * MLA tensor parallelism under -sm graph (DEEPSEEK2/GLM_DSA/MISTRAL4) Extends -sm graph (split-mode graph) to MLA-style attention across the DEEPSEEK2, GLM_DSA, and MISTRAL4 architectures. Previously these archs fell back to -sm layer regardless of the user's flag. Implementation: - Per-rank attention build in build_deepseek2_tp_attention with view-sliced FlashAttention, split-buffer output projection, and ggml_reduce across devices - wk_b / wv_b absorbed weights replicated per device via materialize() in llm_prepare_mla (these can't live in a split buffer) - KV cache replication path (replicated_k_l) for graph-mode TP - distribute_mla_tensors_for_split_mode_graph routes attention/norm tensors into ctx_split; expert tensors stay per-layer - Implements ggml_backend_cuda_split_buffer_get_tensor for the replicated / row-split / col-split inverse paths - Early-reject guard in src/llama.cpp that auto-downgrades -sm graph to -sm layer (with a warning) when incompatible loader flags are set: -ncmoe, -cmoe, -ot, -rtr, -muge New CLI flag: - -gap | --graph-attn-precision <f16|f32> (default f16) See the PR description for the full validation matrix (3 archs x 2/4/8 GPU counts), perf numbers, VRAM accounting, and known limitations. * Some tweaks * materialize lambda: per-head split for graph-mode tp_replicate 7dd19e19 changed wk_b/wv_b distribution from mirror to per-head split (split_dim=2) via prepare_split_tensors. That path only fires when wk_b/wv_b are loaded from GGUF. Models that store only wkv_b in GGUF derive wk_b/wv_b at load via llm_prepare_mla, going through the materialize lambda, which was untouched and still produced mirror replicas (split_dim=-1, full n_head per device). build_deepseek2_tp_attention now does mul_mat(wk_b_local, q_nope_perm) without the prior view_3d slice, so a mirror replica passes an n_head tensor where the kernel expects n_head_local. Result: silent SIGSEGV right after model load. Mirror logic in materialize is replaced with the same per-head split as prepare_split_tensors: head_offsets derived from wo split, each rank gets a tensor with ne[2]=n_head_local, data copied from the appropriate source byte slice. Singular `computed` tensor keeps full metadata for tensors_by_name lookups. Tested: 8x3090, -sm graph -mla 3 -fa on now boots cleanly and sweep-benches without crash. Log confirms new path: "Computed blk.X.attn_k_b.weight ... split across N devices on dim=2". * cleanup: indent fix + remove dead view_3d slicing and debug printf - build_deepseek2.cpp: re-indent the self_attention block in build_deepseek2_layer_attention (lines 253-670). Block was at column 0 inside a function body; now at the expected 4/8-space indent. - build_deepseek2.cpp: drop the commented-out view_3d slicing and debug printfs left over after 7dd19e19's switch to direct mul_mat on per-rank wk_b_local / wv_b_local. Update the stale 'wk_b is replicated (split_dim=-1)' comment to match the new split_dim=2 reality. - ggml-cuda.cu: remove the leftover debug printf in ggml_backend_cuda_split_buffer_get_tensor. No behavior change. Verified with a clean rebuild and DSV2.5 + GLM-4.7-Flash sweep-bench runs. * llm_load_tensors: gate incompatible-flag warning to MLA archs The -ncmoe / -rtr / -muge / -ot warning under -sm graph currently fires for all archs that support graph mode. That's an over-reach: the incompatibility is specific to the MLA TP paths (DEEPSEEK2, GLM_DSA, MISTRAL4) — Gemma4 graph mode existed pre-PR and works with those flags. Gate the warning to MLA archs only. Also refreshes two stale comments left over from the wk_b/wv_b mirror -> per-head-split rewrite: - src/llama.cpp llm_prepare_mla: "Replicate wk_b/wv_b ..." now reads "Per-head split wk_b/wv_b ..." to match what the materialize lambda actually does post-823a39e2. - src/llama-load-tensors.cpp distribute_mla_tensors_for_split_mode_graph: drop the wkv_b row-split mention (wkv_b is no longer created under graph mode after 7dd19e19) and correct the wk_b/wv_b distribution description (per-head split, not per-device replicated). --------- Co-authored-by: Kawrakow <iwankawrakow@gmail.com>	2026-05-19 08:36:17 +03:00
KawrakowandGitHub	1f8c603d9c	Quantize: add extra output tensor for MTP (#1810) ... * Quantize: add extra output tensor for MTP * Consistently use --mtp-requantize-output-tensor	2026-05-17 13:59:56 +03:00
KawrakowandGitHub	3e573cfea6	MTP: option to use re-quantized output tensor for better TG performance (#1809) ... * Option to use re-quantized output tensor for MTP * Remove quantize extra output option * Handle interleaved types	2026-05-16 14:40:18 +03:00
Samuel Oliveira AlvesandGitHub	f4f4b3ff26	Allow dual speculative decoding (#1789) ... * wip: test logic to use multiple specs * feat: introduce composite speculative decoding stages * handle MTP context and draft invalidation * fix: allow gemma mtp for speculative stages * fix: normalize spec stage keys * refactor: remove enable_mtp flag and improve speculative stage handling * fix: update cached text tokens handling for stage chains * feat: implement sync for external MTP after non-MTP accept	2026-05-15 10:10:40 +03:00
Samuel Oliveira AlvesandGitHub	40b65d8f54	feat: add support for draft imatrix output file (#1803)	2026-05-15 08:10:58 +03:00
ubergarmandGitHub	ca52a825db	feat: add --threads-mtmd for independent multimodal thread count (#1797) ... Add `-tm` / `--threads-mtmd` to control CPU thread count used during multimodal image/audio processing (mmproj encoding), separate from the main LLM thread count. This allows running the LLM on GPU with minimal CPU threads (e.g. `-t 1`) to reduce sync overhead, while using many threads (e.g. `-tm 16`) for CPU-bound mmproj encoding with `--no-mmproj-offload`. Fallback chain when `-tm` is not specified: 1. `--threads-batch` (-tb) — multimodal encoding is a batch/prefill-like operation, so it makes sense to track with batch thread count 2. `--threads` (-t) — final default Works with both mtmd-cli and llama-server. AI: ubergarm/Qwen3.6-27B-GGUF MTP IQ4_KS 15.113 GiB (4.752 BPW) + pi.dev	2026-05-13 17:44:43 +03:00
ubergarmandGitHub	f478a3ec0b	fix: only inflate n_batch for GPU-offloaded mmproj, not CPU (#1788) ... The get_batch_ubatch() function unconditionally inflated n_batch and n_ubatch whenever --mmproj was specified, regardless of whether the mmproj model actually ran on the GPU. This boosted batch size applies to both the main context and the MTP draft context, since params_base.speculative.cparams_dft is derived from common_context_params_to_llama(params_base). When mmproj runs on CPU (--no-mmproj-offload), this batch inflation is unnecessary for mmproj itself (CPU compute is sized by image dimensions independently), but it still inflates the MTP compute buffer proportionally. For large images (e.g. --image-max-tokens 4096), the MTP compute buffer ballooned to ~2020 MiB and triggered an OOM even though the mmproj model was fully on CPU and should have saved VRAM. Restrict the batch inflation to !params.mmproj.path.empty() && params.mmproj_use_gpu so it only triggers when mmproj actually occupies GPU memory. When mmproj runs on CPU, the existing per-chunk decode splitting in mtmd_helper_decode_image_chunk_impl handles large images correctly with the default batch size. AI: ubergarm/Qwen3.6-27B-GGUF MTP IQ4_KS 15.113 GiB (4.752 BPW) + pi.dev	2026-05-13 09:08:42 +03:00
Samuel Oliveira AlvesandGitHub	c2b8bca807	Add MTP Support for Gemma 4 (#1744) ... * gemma-mtp: build the arch to load the MTP model * gemma-mtp: fix mtp kv state * gemma-mtp: refactor some functions and create gguf * gemma-mtp: make usable for embeddings models variant * gemma-mtp: fix qwen mtp load in graph split * gemma-mtp: refactor tensor creation and adjust output tensor handling * Gemma 4 MTP: improve tensor handling, and adjust split mode logic	2026-05-10 07:44:20 +03:00
dungquixote42andGitHub	b93721902b	Add Expiring Logit Bias (#1731) ... * initial commit * fix substr() out of range * add tilde (~) as bias range indicator * fix runtime error when the first entry is exitword	2026-05-06 09:25:38 +03:00
Samuel Oliveira AlvesandGitHub	ea94afe777	Speculative checkpoints for recurrent models (#1669) ... * server: spec checkpoints for recurrent models * fix: save/restore sampler state during speculative checkpoint When speculative decoding rejects draft tokens and restores the recurrent state checkpoint, the sampler (RNG, grammar, prev tokens) must also be restored to maintain consistency. Without this, the sampler state reflects the rejected draft tokens, leading to potential divergence. Uses common_sampler_clone() to snapshot the sampler before the speculative batch decode, and restores it on rejection. * server: snapshot recurrent state in tensor * reset ngram mod state for rejected tokens * server: refactor checkpoint state logic * speculative: fix sampler for checkpoints * recurrent model: implement recurrent kernel checkpoint * recurrent model: refactor api * spec: free rbudget before overwriting	2026-04-24 09:59:30 +02:00
4 people	e0596bf614	Autoparser - complete refactoring of parser architecture (#1376) ... * Autoparser - complete refactoring of parser architecture Autoparser: add optional argument reshuffle capability Autoparser: True streaming (#20177) * Relax atomicity constraint for nicer, more pleasent, True Streaming parsing * Whitespace * Remove redundant atomics Revert to OAI-compatible args (#20213) * Revert to OAI-compatible args * Apply workaround::func_args_not_string Fix structured outputs (#20223) * Fix structured outputs * Update common/chat-auto-parser-generator.cpp Co-authored-by: Aldehir Rojas <hello@alde.dev> --------- Co-authored-by: Aldehir Rojas <hello@alde.dev> Fix compile bug (#20203) * Fix compile bug * Update common/chat-auto-parser-helpers.cpp Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com> --------- Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com> # Conflicts: # common/chat-auto-parser-helpers.cpp common : gracefully handle incomplete output (#20191) * common : handle incomplete UTF-8 at end of input in PEG parser * cont : if reached end prematurely, emit needs_more_input to propagate partial output * cont: refactor peg parse context to add lenient flag * cont : remove partial flag, keep lenient flag PEG parser for LFM2 (#20251) * PEG parser for LFM2 * Simplify using python_value() common: map developer role to system (#20215) * Map developer role to system * Simplify common: consolidate PEG string parsers (#20263) * common : consolidate PEG string parsers * cont : fix json_string_content() examples : fix empty items in json_schema_to_grammar.py [no ci] (#19968) * Fix logic for retrieving schema items in `json_schema_to_grammar.py` If `schema['items']` is `{}` and `prefixItems not in schema', as `{}` is Falsy, the original code here will raise an error. I think if `schema['items']` is `{}`, them items should just be `{}` * Apply suggestion from @CISC Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com> * Add tests for arrays with empty items Add two unit tests to `tests/test-json-schema-to-grammar.cpp` that validate handling of arrays when 'items' is an empty schema and when 'prefixItems' is present alongside an empty 'items'. Both tests expect the same generated grammar, ensuring the JSON Schema->grammar conversion treats an empty 'items' schema (and the presence of 'prefixItems') correctly and covering this edge case. --------- Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com> Reduce level of content parser warning message to avoid log spam on non-debug verbosity (#20347) do not return if template parse failed add arg to enable parallel tool call common : fix incorrect uses of stoul (#20313) # Conflicts: # common/arg.cpp # src/llama-grammar.cpp examples : fix empty items in json_schema_to_grammar.py [no ci] (#19968) * Fix logic for retrieving schema items in `json_schema_to_grammar.py` If `schema['items']` is `{}` and `prefixItems not in schema', as `{}` is Falsy, the original code here will raise an error. I think if `schema['items']` is `{}`, them items should just be `{}` * Apply suggestion from @CISC Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com> * Add tests for arrays with empty items Add two unit tests to `tests/test-json-schema-to-grammar.cpp` that validate handling of arrays when 'items' is an empty schema and when 'prefixItems' is present alongside an empty 'items'. Both tests expect the same generated grammar, ensuring the JSON Schema->grammar conversion treats an empty 'items' schema (and the presence of 'prefixItems') correctly and covering this edge case. --------- Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com> Add support for MiroThinker with new jinja template common/parser: handle reasoning budget (#20297) * v1 * Finished! * Handlie cli * Reasoning sampler * Apply suggestions from code review Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com> * Less explosive terminology :) * Add utf-8 case and tests * common : migrate reasoning budget sampler to common * cont : clean up * cont : expose state and allow passing as initial state * cont : remove unused imports * cont : update state machine doc string --------- Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com> Co-authored-by: Alde Rojas <hello@alde.dev> common/parser: use nlohmann::ordered_json to preserve parameter order (#20385) common/parser: add GigaChatV3/3.1 models support (#19931) Co-authored-by: Mishusha <pmv26021975@gmail.com> common/parser: gracefully handle undetected tool parser, print error message. (#20286) fix: prevent nullptr dereference (#20552) common : fix iterator::end() dereference (#20445) # Conflicts: # common/regex-partial.cpp jinja : add capability check for object args (#20612) common/parser: add `--skip-chat-parsing` to force a pure content parser. (#20289) * Add `--force-pure-content` to force a pure content parser. * Update common/arg.cpp Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com> common : rework gpt-oss parser (#20393) * common : rework gpt-oss parser * cont : fix gpt-oss tests * cont : add structured output test * cont : rename final to final_msg common : fix gpt-oss content removal (#20745) common/parser: add proper reasoning tag prefill reading (#20424) * Implement proper prefill extraction * Refactor cli parameters, update docs, move reasoning budget sampler part to common/reasoning-budget.cpp * Update tools/server/server-task.cpp * refactor: move grammars to variant, remove grammar_external, handle exception internally * Make code less C++y Co-authored-by: Georgi Gerganov <ggerganov@gmail.com> chat : handle tool calls with no required args in TAG_WITH_TAGGED format (#20764) * chat : handle tool calls with no required args in TAG_WITH_TAGGED format * Update tests/test-chat.cpp [no ci] Co-authored-by: Aldehir Rojas <hello@alde.dev> --------- Co-authored-by: Piotr Wilkin (ilintar) <piotr.wilkin@syndatis.com> Co-authored-by: Aldehir Rojas <hello@alde.dev> common/parser : fix out_of_range crash in throw path (#20424 regression) (#20777) * chat : fix out_of_range crash in throw path (#20424 regression) #20424 introduced effective_input = generation_prompt + input, but the throw path uses input.substr(result.end) where result.end is a position within effective_input. Every thinking model with a non-empty generation_prompt crashes with std::out_of_range instead of the intended error message. Test crashes on unpatched master, passes with fix: cmake -B build -DLLAMA_BUILD_TESTS=ON -DLLAMA_BUILD_TOOLS=OFF cmake --build build --target test-chat ./build/bin/test-chat * Update test-chat.cpp * Update test-chat.cpp * Update test-chat.cpp --------- Co-authored-by: Piotr Wilkin (ilintar) <piotr.wilkin@syndatis.com> jinja : fix heap OOB read in value equality comparison (#20782) Address GHSA-q9j6-4hhc-rq9p and GHSA-2q4c-9gq5-5vfp. The three-iterator overload of std::equal in value_array_t::equivalent() and value_object_t::equivalent() reads past the end of the shorter container when comparing arrays or objects of different lengths. Use the four-iterator overload (C++14) which checks both range lengths. Found-by: Pwno common : fix typo in debug log ('extracft' -> 'extract') (#20807) common/parser: fix nasty bug causing subtle corruption of generation prompt (#20825) jinja : refactor token advancement (#20864) * refactor token advancement * exercise sub-expressions common/autoparser : detect reasoning markers when enable_thinking changes system prompt (#20859) common : replace wrap_for_generation with a prefix convenience function and fix gpt-oss (#20912) jinja: fix macro with kwargs (#20960) * jinja: fix macro with kwargs * Apply suggestions from code review Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com> * fix newline problem --------- Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com> common : inhibit lazy grammar sampler while reasoning is active (#20970) * common : inhibit grammar while reasoning budget is active * cont : update force_pos in accept * cont : fix tests * cont : tweak should apply logic * cont : return early not using grammar sampler * Add tests * cont : prevent backend sampling when reasoning budget enabled * cont : fix typo --------- Co-authored-by: Piotr Wilkin <piotr.wilkin@syndatis.com> # Conflicts: # common/reasoning-budget.h # common/sampling.cpp # tools/cli/cli.cpp # tools/server/server-common.cpp # tools/server/server-task.cpp common/parser: fix reasoning whitespace bugs + extra parser tests (#21085) * fix whitespace reasoning issues + add reconstruction tests * Proper fix * fix Nemotron autoparser test expectations to include newline in marker common : add reasoning_format = none support to gpt-oss (#21094) common/json-schema: fix: handle non-capturing groups (?:...) in JSON schema pattern converter (#21124) The regex-to-grammar converter in _visit_pattern() crashes with SIGSEGV when a JSON schema "pattern" field contains a non-capturing group (?:...). Root cause: when the parser sees '(' followed by '?', it pushes a warning but does not advance past '?:'. The recursive transform() call then interprets '?' as a quantifier and calls seq.back() on an empty vector, causing undefined behavior. This commonly occurs when serving OpenAI-compatible tool calls from clients that include complex regex patterns in their JSON schemas (e.g., date validation patterns like ^(?:(?:\d\d[2468][048]|...)-02-29|...)$). The fix: - Skip '?:' after '(' to treat non-capturing groups as regular groups - For unsupported syntax (?=, ?!, etc.), skip to matching ')' safely, handling escaped characters to avoid miscounting parenthesis depth - Adjust the ')' unbalanced-parentheses check using direct char comparisons instead of substr - Add test cases for non-capturing groups (C++ only, as the JS/Python implementations do not yet support this syntax) common/parser: fix handling of tool definition with missing properties key (#21128) jinja : handle empty expressions correctly (#20913) * Reject empty computed member expressions before returning slices[0] from parse_member_expression_arguments(). * Treat empty computed member expressions with Jinja2 undefined semantics Treat empty computed member expressions like `a[]` as undefined instead of raising a parser error, to match Jinja2 behavior. - return a noop expression for empty computed member arguments - return undefined when a computed member key evaluates to undefined - add Jinja tests covering `a[]|default('fallback')` and `a[] is undefined` * Handle undefined computed member properties Move undefined-property handling to the common member access path, and add a test covering `a[undefined] is undefined`. * Use default undefined value in member access Initialize val and then return it when property is undefined. Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com> * empty statement parses to blank_expression instead of noop_statement --------- Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com> common : gpt-oss handle builtin and unsolicited tool calls (#21213) fix: tool call parsing for LFM2 and LFM2.5 models (#21242) * fix: tool call parsing for LFM2 and LFM2.5 models' * refactor: add test / break out lfm2 and lfm2.5 parsing logic # Conflicts: # common/chat.cpp Relax prefill parser to allow space. (#21240) * Relax prefill parser to allow space. * Move changes from prefix() to parser generation * Only allow spaces if we're not having a pure content parser next common : add commentary rules for gpt-oss-20b (#21286) add reasoning budget model, mtmd: fix gguf conversion for audio/vision mmproj (#21309) * fix gguf conversion for audio/vision mmproj * fix test # Conflicts: # convert_hf_to_gguf.py # examples/eval-callback/eval-callback.cpp # examples/mtmd/CMakeLists.txt # examples/mtmd/clip-impl.h # examples/mtmd/mtmd.cpp # gguf-py/gguf/constants.py # gguf-py/gguf/gguf_writer.py # gguf-py/gguf/tensor_mapping.py # src/CMakeLists.txt # src/llama-arch.cpp # src/llama-arch.h # src/llama-model.cpp # src/llama-model.h # src/llama-vocab.cpp # src/models/models.h # tests/test-llama-archs.cpp # tools/mtmd/clip-graph.h # tools/mtmd/clip-model.h # tools/mtmd/clip.cpp # tools/mtmd/models/models.h fix: gemma 4 template (#21326) chat : avoid including json in chat.h (#21306) jinja: coerce input for string-specific filters (#21370) common : fix tool call type detection for nullable and enum schemas (#21327) * common : fix tool call type detection for nullable and enum schemas * common, tests : fix grammar delegation for nullable/enum schemas and add tests Fix enum type inference to scan all enum values (not just index 0) so schemas like {"enum": [0, "celsius"]} correctly detect string type. Fix schema_delegates in peg-parser to handle nullable type arrays (["string", "null"]) and typeless enum schemas in raw mode, allowing the tagged parser to use raw text instead of JSON-formatted strings. Add test cases for Qwen3-Coder (TAG_WITH_TAGGED format): - nullable string ["string", "null"] - nullable string with null first ["null", "string"] - nullable integer ["integer", "null"] - enum without explicit type key common/parser: fix call ID detection (Mistral parser mostly) + atomicity for tag-json parsers (#21230) * Fix call ID detection (Mistral parser mostly) + atomicity for tag-json parsers * Rename * Update common/chat-auto-parser-generator.cpp Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com> --------- Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com> common : add gemma 4 specialized parser (#21418) * common : add gemma4 dedicated parser * cont : add '<|tool_response>' as eog * cont : emit JSON from Gemma4 tool call AST * cont : more fixes * cont : refactor convert function * cont : refine rules and mapping * cont : add more tests * cont : clean up * cont : remove autoparser gemma4 implementation * cont : more cleanup * cont : rename gemma4.jinja to match the others * cont : add custom template to support interleaved thinking * cont : preserve reasoning in model turns * cont : fix initializer error * cont : fix unused vars * cont : fix accidental static * cont : fix specialized_template signature * fix extra semicolon * remove debug line and extra space [no ci] fix reasoning budget parser: fix MiniMax handling (#21573) jinja : support ensure_ascii=true, string repetition and int/float self-filtering (#21623) * feat: jinja engine improvements for reka-edge Port three Jinja engine improvements needed for the reka-edge model: 1. Python-style string repetition ("ab" * 3 → "ababab") 2. ensure_ascii=true support for tojson filter (escapes non-ASCII to \uXXXX) 3. int() builtin on value_int_t (identity, needed for Reka Edge template) * fix: escape invalid utf8 bytes when ensure_ascii=true The json_ensure_ascii_preserving_format function does not correctly handle an edge case where if UTF-8 parsing fails, it adds the non-ascii character back to the output as a raw byte. This commit fixes that by adding the unicode standard replacement character \\ufffd to the output instead. This is the standard behavior for various programming languages like Python, Rust, Go, etc. * chore: address PR comments 1. Add todo comment for supporting string repetition for array/tuples 2. Add support for float identity operation 3. Move invalid ascii test case to test_fuzzing * chore: accept suggestion for common/jinja/value.cpp Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com> --------- Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com> common : simplify autoparser tagged parser rules (#21216) * common : simplify autoparser tagged parser rules * cont : remove upper limit on optional args * cont : revert changes to parsing at the end * cont : undo arbitrary ordering of optional args * cont : fix uninitialized required parameters * revert to simplify merge * re-apply patches * restore flexible optional arg ordering tests common : fix ambiguous grammar rule in gemma4 (#21661) * common : fix ambiguous grammar rule in gemma4 * cont : fix missing comma... common : enable reasoning budget sampler for gemma4 (#21697) * fix: enable reasoning budget sampler for gemma4 Add thinking_start_tag and thinking_end_tag to common_chat_params_init_gemma4(). Without these, the reasoning budget sampler never activates for gemma4. Make the newline after "thought" optional in the PEG parser to handle budget=0 (sampler forces end tag before the newline). Add test case for empty thinking block. Fixes #21487 * use p.space() instead of p.optional(p.literal("\n")) in gemma4 thought parser common : better align to the updated official gemma4 template (#21704) fix: Fix broken structured output when using $refs in json_schema (#21699) chat: dedicated DeepSeek v3.2 parser + "official" template (#21785) Hide render_message_to_json warning common/gemma4 : handle parsing edge cases (#21760) common: skip reasoning budget sampler when no budget is requested (#21870) * common: skip reasoning budget sampler when no budget is requested After I added thinking_start_tag / thinking_end_tag for gemma4 in #21697, the reasoning budget sampler gets unconditionally created even when no budget is configured (the default -1). The same applies to kimi_k2, lfm2, lfm2_5, and ministral_3 which also set these tags. The budget gets converted to INT_MAX, so the sampler never actually forces any tokens but still runs per-token checks (start tag matching in IDLE state, token-to-piece conversion + UTF-8 checks in COUNTING state). More importantly, the mere existence of the sampler (non-null rbudget) disables backend sampling. Backend sampling lets the GPU select tokens directly, avoiding a full logits transfer from GPU to CPU every token. This could explain the 30% speed regression reported in #21784 (98 t/s to 70 t/s on Vulkan). So I added a reasoning_budget_tokens >= 0 check to the sampler creation condition. When the budget is unlimited, the sampler is not created, backend sampling stays enabled, and no per-token overhead is added. When a budget is explicitly set (0, 128, 1024, etc.), the sampler is created and works as before. * common: preserve rbudget when grammar is lazy Following up on the review feedback on #21870: keep the reasoning budget sampler when grammar_lazy is true, so the thinking-block grammar suppression from #20970 still works when tools are in use. This way, we only skip the sampler when both no budget is set AND grammar is not lazy. autoparser: support case of JSON_NATIVE with per-call markers (test case: Reka-Edge) (#21892) * fix grammar * fix add sampled token --------- Co-authored-by: Piotr Wilkin (ilintar) <piotr.wilkin@syndatis.com> Co-authored-by: firecoperana <firecoperana>	2026-04-22 10:04:13 +02:00
Samuel Oliveira AlvesandGitHub	260622faf6	Self-decoding: Adds support for suffix decoding (#1646) ... * speculative: implement suffix-tree decoder * speculative: add support to cache and tuner	2026-04-18 16:10:10 +02:00
dmaivelandGitHub	4f4bcfbe67	Add --defer-experts flag to defer expert mmap residency on Linux (#1634) ... * Add --defer-experts flag to defer expert mmap residency on Linux * Disable warmup when defer-experts is enabled	2026-04-16 08:54:44 +02:00
dungquixote42andGitHub	869b83bc49	Add Unicode allowlist (#1597) ... * initial commit * cleanup * fix whitelist arg parsing and simplify keyword search state * rename white* to allow* * add vocab_pieces init function, rename update functions, delete accidentally added file * delete temporary bias code * auto-generate fill function with script data inside * deduplicate allowlist unicode rule parsing * minor cleanup * delete unnecessary header * refactor allowlist to support sequential rule sets via keywords * add early exit for zero-rules case * delete accidentally added file	2026-04-10 18:22:57 +02:00
KawrakowandGitHub	9db5d9907e	Mixed KV cache (#1599)	2026-04-09 09:33:17 +02:00
Samuel Oliveira AlvesandGitHub	3de81530c5	Allow tuning of the best args for speculative decoding. (#1595) ... * wip: build spec tuner for spefic args * wip: test different reward system * spec-tune: fix the reward to find best params given a good TPS * spec-tune: refactor logic for its own file * minor clean for comments and modules	2026-04-08 08:02:42 +02:00
KawrakowandGitHub	73742c5db9	mtmd: be able to use alternative types for the K*Q multiplication (#1567) ... * mtmd: allow using types other than f32 for K*Q * Do not cast q if kq_type is quantized * Fix formatting * More formatting	2026-04-02 08:04:05 +02:00
KawrakowandGitHub	9660eb4487	Control compute buffer sizes for large batches (#1560) ... * Worst graph output tokens * This is better	2026-04-01 07:57:52 +02:00
KawrakowandGitHub	a95981013a	V-cache Hadamard transform (#1527)	2026-03-28 11:28:50 +01:00
KawrakowandGitHub	d66dc7c0c4	CUDA: restore pinned memory usage for tensor overrides (#1508)	2026-03-25 17:18:32 +01:00
KawrakowandGitHub	86f4f516e5	Auto-fit offloaded tensors to available VRAM (MoE models) (#1501) ... * WIP: automatically fit model in available VRAM * WIP * This seems pretty solid	2026-03-25 07:29:29 +01:00
3 people	cdf9142aa5	fix grammar stack empty error for qwen3.5 (#1490) ... * fix grammar stack empty error for qwen3.5 * Add to --help --------- Co-authored-by: firecoperana <firecoperana>	2026-03-24 07:48:20 +01:00
KawrakowandGitHub	b7a2bde4cc	Take into account layer sizes for setting GPU layers (cont) (#1476) ... * Also take into account KV cache * Take into account attn_wkv_b and mla = 3 compute buffers	2026-03-23 17:46:53 +01:00
Nexes the ElderandGitHub	6c665f38fd	sweep-bench: add -minilog argument to reduce verbose logging (#1468) ... Purpose: Add --minilog flag to llama-sweep-bench that filters log output to show only essential GPU/layer distribution information while suppressing verbose model metadata and per-layer device assignment messages. Changes: - Add llama_selective_log_callback with blacklist approach (sweep-bench.cpp) Blacklisted patterns (hidden): - Per-layer device assignments ('Setting default device in layer') - KV metadata dump header and entries - Tensor type counts - Model validation messages - EOG/special token cache info - Metadata printout (llm_load_print_meta, print_info) - Layer sizes table - Tensor loading info (llm_load_tensors) - Separator lines - Most common cases of incomplete/continuation lines are also hidden All other log output is shown, including: - GPU VRAM info - Split/buffer distribution per device - Graph split estimates - Final benchmark table and timings	2026-03-20 09:40:56 +01:00
KawrakowandGitHub	9b7db9bc3f	Better --n-cpu-moe (#1464)	2026-03-19 06:57:01 +01:00
3 people	f9b7fe9749	llama: add --dry-run option (#1462) ... Co-authored-by: firecoperana <firecoperana>	2026-03-18 17:20:17 +01:00
KawrakowandGitHub	07ab0d263b	Add ffn_gate_up_exps to --cpu-moe and --n-cpu-moe overrides (#1422)	2026-03-13 17:56:08 +01:00
3 people	4d09e04501	common : add env vars for cache_type_k/v, mlock, k_cache_hadamard and enable env vars for all tools (#1402) ... Two changes: 1. Add four missing environment variable bindings to gpt_params_parse_from_env(): - LLAMA_ARG_CACHE_TYPE_K (string, e.g. "q8_0") - LLAMA_ARG_CACHE_TYPE_V (string, e.g. "q8_0") - LLAMA_ARG_MLOCK (bool, "1"/"true") - LLAMA_ARG_K_CACHE_HADAMARD (bool, "1"/"true") 2. Call gpt_params_parse_from_env() from gpt_params_parse() so that ALL tools (llama-cli, llama-bench, etc.) respect env vars, not just llama-server. Env vars act as defaults; CLI flags override. Follows the existing get_env() pattern and uses the same LLAMA_ARG_ prefix convention as the other env vars. Co-authored-by: Pipboyguy <>	2026-03-11 15:35:26 +01:00
3 people	fd16a418de	Fix clang warnings on macOS (#1354) ... Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>	2026-03-03 16:27:16 +01:00
3 people	8f9e19d57c	server: add checkpoint tolerance and fix grammar_trigger init (#1346) ... Co-authored-by: firecoperana <firecoperana>	2026-03-02 07:45:32 +01:00
KawrakowandGitHub	0ff3a43289	Bring back #1333 and #1335 (#1340) ... * Bring back fused delta net 3 * Remove autoregressive and chunking	2026-02-28 14:31:42 +01:00