* vulkan/cpu: Support f16 as SET_ROWS src.
This adds full support for f16 SET_ROWS (equivalent to f32) to vulkan and CPU
backends, and adds more backend tests.
* Set DenormPreserve 16 when supported, to try to fix failures on Intel
* tune error threshold
* update metal supports_op
* ggml: uniformize im2col dst_type for all conv ops
* Update ggml/src/ggml.c
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
* ggml : uniformize im2col casting logic across all conv ops
* fix : allow im2col_f16 to accept any kernel type
---------
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
* model: add Hy3 (hy_v3) architecture support
Adds Tencent Hunyuan 3 (HF architecture HYV3ForCausalLM, GGUF arch
hy_v3): a MoE decoder stack with per-head Q/K RMSNorm, a sigmoid
router with expert selection bias, an always-active ungated shared
expert, and leading dense block(s) (first_k_dense_replace).
The base implementation is ported from charlie12345's fork
(https://github.com/charlie12345/ROCmFPX, src/models/hyv3.cpp),
adapted to current mainline APIs (hparams.n_layer(), build_qkv,
build_moe_ffn with fused gate_up + scale tensors, output_s).
Note: blk.N.exp_probs_b is stored without a .bias suffix for
compatibility with existing hy_v3 GGUFs produced by that fork.
Co-Authored-By: charlie12345 <charlie12345@users.noreply.github.com>
Co-authored-by: Piotr Wilkin <ilintar@gmail.com>
Assisted-by: Claude Fable 5
* tests: Harmonize the use of private ggml includes
* tests: In test-backend-ops, use quoted includes
As with all other tests. This is to ensure that the build uses shipped
headers over possibly system-installed ones.
* chat : fix reasoning leak with force-opened bare <think> templates
The reasoning start tag inferred from prior turns can carry trailing
whitespace (e.g. <think>\n) while a force-open template prefills a bare
<think>. Trim the tag used for the prefix split so the bare prefill is
matched instead of being swallowed into content.
* chat : fix Nemotron Nano v2 regression
---------
Co-authored-by: Alde Rojas <hello@alde.dev>
* server: honour per-request reasoning_budget_tokens in chat completions
The reasoning-budget block in oaicompat_chat_params_parse read only the
server-level default (opt.reasoning_budget, typically -1) and the
Anthropic-style alias thinking_budget_tokens, but never the canonical
reasoning_budget_tokens field from the request body. Because the key
was then written into llama_params before the generic body-copy loop
ran, the copy loop found the key already present and silently skipped
the caller-supplied value. Any per-request override (e.g. 0 to
suppress thinking entirely) was therefore discarded.
Fix: read reasoning_budget_tokens from the request body first, so the
value that reaches the sampling layer is the one the caller intended.
Add a unit test in test-chat.cpp that exercises this path via
oaicompat_chat_params_parse with a Qwen3 template (which the autoparser
detects as a thinking-capable model) and asserts the returned
llama_params carries reasoning_budget_tokens == 0.
* server: honour per-request reasoning_budget_message in chat completions
The reasoning-budget block in oaicompat_chat_params_parse wrote
reasoning_budget_message into llama_params straight from the server-level
default (opt.reasoning_budget_message) and never read the canonical
reasoning_budget_message field from the request body. Because the key
was written before the generic body-copy loop ran, that loop found the
key already present and silently skipped the caller-supplied value. Any
per-request override of the message injected before the end tag when the
budget is exhausted was therefore discarded, even though server-task.cpp
already reads reasoning_budget_message from that data.
This mirrors the reasoning_budget_tokens bug fixed in the previous commit.
Fix: read reasoning_budget_message from the request body first, falling
back to the server default, so the value that reaches the sampling layer
is the one the caller intended.
While here, collapse the adjacent reasoning_budget_tokens override to a
single json_value() call; json_value already falls back to the default on
a missing/null/wrong-type key, so the explicit body.contains() guard was
redundant. No behavioral change.
Add a unit test in test-chat.cpp that exercises this path via
oaicompat_chat_params_parse with a Qwen3 template (which the autoparser
detects as a thinking-capable model) and asserts the returned
llama_params carries the per-request reasoning_budget_message rather than
the server default.
* cleanup
---------
Co-authored-by: Xuan Son Nguyen <son@huggingface.co>
* Use smart pointers in test_case::eval
This makes it consistent with other methods of `test_case`.
* Use smart pointer in show_test_coverage also
* Also use smart pointers for backends
* metal : add CONV_2D_DW (depthwise 2D convolution) support
* test : add perf cases for CONV_2D_DW
* metal : use 3D dispatch for CONV_2D_DW kernel
* metal : add channel-tiled CONV_2D_DW kernel for non-contiguous layouts
* metal : simplify CONV_2D_DW dispatch and trim comments
* metal : merge duplicate CONV_2D_DW pipeline getters
* tests : add F16 CONV2D_DW tests
* cpu : fix F16 kernel support for CONV_2D_DW
* tests : remove commented-out CONV_2D_DW test block
---------
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
* ggml : add support for CPU f16->f16 GGML_OP_SET_ROWS
* ggml : add missing type checks in f16 GGML_OP_SET_ROWS
* ggml : merge ggml_compute_forward_set_rows_f32() and ggml_compute_forward_set_rows_f16() into ggml_compute_forward_set_rows_impl()
* chore : replace assert() with GGML_ASSERT()
---------
Co-authored-by: Stanisław Szymczyk <sszymczy@gmail.com>
* chat: trim messages sent to StepFun parser (fixes long reasoning loops)
* add regression test; remove duplicate template
* chat: trim StepFun content parts before rendering
The StepFun trim workaround ran on the already-rendered messages, where
typed content parts have been concatenated into a single string, so the
per-part whitespace could no longer be reached. Move the trim ahead of
rendering and apply it to content_parts text as well as the string
content and reasoning_content. Adds a content-parts regression test.
Co-Authored-By: Piotr Wilkin <ilintar@gmail.com>
Assisted-By: Claude Fable 5 <noreply@anthropic.com>
---------
Co-authored-by: tarruda <tpadilha84@gmail.com>
* cuda: enable topk-moe fusion for 288 experts
The topk-moe fusion only accepted power-of-2 expert counts (or the
special-cased 576), so models with 288 experts (e.g. Step-3.7-Flash)
fell back to the unfused per-layer routing chain: softmax/sigmoid,
argsort, get_rows, sum_rows, div, clamp, scale. At batch size 1 that
is ~330 extra tiny graph nodes per token.
288 is a multiple of the warp size, so the existing kernel already
handles it; this adds the missing template instantiation and accepts
288 in the eligibility check.
Measured on gfx1151 with Step-3.7-Flash IQ4_XS (llama-bench,
-b 4096 -ub 4096 -fa 1 -dio 1 -ctk q8_0 -ctv q8_0; machine idle,
before/after paired so pp4096 stays matched as a load control):
test | before | after
----------------+----------------+----------------
pp4096 | 460.99 ± 0.45 | 462.47 ± 0.34 (unchanged)
tg128 | 19.10 ± 0.04 | 19.56 ± 0.03 (+2.4%)
tg128 @ d30000 | 12.68 ± 0.04 | 12.69 ± 0.03 (unchanged)
Prompt processing is unaffected (the fusion only touches decode
routing). The decode gain is ~+2.4% at shallow context and fades with
depth: by 30k tokens each step is attention-bound over the KV cache,
so removing the fixed routing overhead is no longer visible.
Assisted-By: Claude Fable 5 <noreply@anthropic.com>
* Update tests/test-backend-ops.cpp
Co-authored-by: Oliver Simons <osimons@nvidia.com>
* Add comment for case 288 in topk-moe.cu
---------
Co-authored-by: Oliver Simons <osimons@nvidia.com>
* convert: add dsv4 conversion
* add basic setup
* add llm_graph_input_dsv4
* add save-load state
* add sinkhorn eps - correction by @fairydreaming
* add rope fix
* cleanup dead code
* fix bugs
* support pro model: added by @fairydreaming
* remove redundant V cache
* Chat template
* remove debugging leftovers
* Add mechanism for inlining templates based on architecture
* s/deepseek-v4-flash/deepseek4/g
* s/deepseek-v4-flash/deepseek4/g continued
* enable graph reuse
* enable FA
* fix test llama archs
* rename
* compatibility with antirez ds4 GGUFs
* simplified set_gguf_parameters() by calling super class method, replaced moe.score_func with expert_gating_func.
* reserve worst-case kv-cache
* revert max split inputs
* address review comments
* add padding to enable FA
* pad only the final value of plan.n_kv to 256
* remove built-in cpp chat template
* cont: remove cpp built-in template
* rm outdated test
* replace ggml_view_3d() with ggml_reshape_3d()
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
* only support n_seq=1 for now
* remove unused var
* cont: remove unused var
* use scale bias
* use correct ptr for can_reuse
* remove gen-chat-inline-templates.py
* simplify graph reuse
* cont: cleanup
* remove unused inputs
* enable partial checkpointing
* add correct shape for kq_mask + set llama_model_n_swa to 0 for dsv4
* precompute source_idx + add comment about dummy write
* support multi-seq
* remove restored_trim_pos
* use split_equal when possible
* fix indent
* address review comments
* use LLM_KV
* fix ci
---------
Co-authored-by: Piotr Wilkin <piotr.wilkin@syndatis.com>
Co-authored-by: Stanisław Szymczyk <sszymczy@gmail.com>
Co-authored-by: Xuan Son Nguyen <son@huggingface.co>
Co-authored-by: fairydreaming <166155368+fairydreaming@users.noreply.github.com>
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
* [CUDA] Added a cudaMemcpy2DAsync fast path to ggml_cuda_cpy
Add a CUDA ggml_cpy fast path for same-type, same-shape strided copies that are just 2D pitched block copies.
When tensors are not fully contiguous but each row is contiguous, it now uses cudaMemcpy2DAsync instead of the slow element-wise scalar copy kernel.
This fixes the GDN recurrent snapshot update with -np 4, where rollback slots are separated by cache stride gaps.
* Add new tests that execute the new optimized strided copy path
* Return unsupported for strided copy in OpenVINO, as new tests are failing
Tests are generally prefixed with -test, so rename export-graph-ops
accordingly.
rpc-server is probably too generic a name for /usr/bin. Because it
should work with any ggml application, it is renamed to ggml-rpc-server.
* ggml-cpu: fix SVE leftover path in ggml_vec_dot_f32
2D convolutions with kernel size 9 produced different results on SVE
enabled ARM devices. After debugging it turned out that ggml_vec_dot_f32
was using data from inactive lanes.
Use svmla_f32_m(pg, sum1, ax1, ay1) so inactive lanes retain sum1.
* cont : clean-up
---------
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
* hex-mm: new weight layout and fusion updates
* hvx-mm: unroll the new tiled vec_dots to optimize hvx register util
* hex-mm: optimize dyn.quant format for q8_0 and q8_1 to reduce overhead in vec_dots.
* hvx-mm: parallel quantizer per block for large rows
* hvx-mm: simplify and futher optimize dyn.quant and vec_dots
* hvx-mm: keep intermediate per tile accumulators in fp16
* hmx-mm: optimize weight dequant by aligning the repacked tiles with the DMA
* hmx-mm: remove qweight scratch and just use vtcm_weight
* hmx-mm: remove all unused and obsolete code
* hmx-mm: the new tiled repack format is here to stay -- rename all x4x2 to _tiled
* hmx-mm: improve activation processing with dma prefetch
* hex-mm: fix hmx/hvx fallback logic and MUL_MAT_ID allocation (unbreaks OLMoE)
* hex-mm: align the weight tiles with dma just like we did in hmx-mm
* hex-mm: factor out common mm bits into htp/matmul-ops.h
* hex-mm: start moving mm kernel selection to the host
* hex-mm: move all of the matmul param compute into the host
* hmx-mm: restore pipelined mode
* hmx-mm: unroll the dequant functions to optimize register usage
* hmx-mm: further improve activation process
* hex-mm: use vtcm_seq_alloc for all vtcm allocations and define more common functions
* hex-mm: improve mm optimizer to acount for number of activation threads
* hex-mm: fix matmul-id kernel params selection (unbreaks OLMoE and LFM)
* hexagon: remove support for arch < v73 since HMX is now required for most use-cases
* hex-mm: cleanup naming for consistency
* hex-mm: make sure matmul fusion accounts for vtcm allocation
* hex-mm: minor cleanup for kernel_params definition
* hex-mm: replace hardcoded limits with proper checks for vtcm requirements
* hex-mm: add support for non-tiled mm as a fallback option and factor out hvx kernels into separate header
* hex-mm: remove unused functions
* hex-mm: add shorthand for MM_SELECT in run-tool script
* hvx-mm: factor out hvx/hmx microkernels and unify matmul entry and dispatch
* hex-mm: further cleanup matmul fallback path
* hex-mm: refactor matmul entry point and dispatch a bit further
* hexagon: update cmake build to enable hmx for everything
* hex-ops: optimize kernel_param updates and include summary in the logs
* hex-mm: add support for GGML_HEXAGON_MM_SELECT
* hex-mm: add hex-common header
* hex-mm: pass correct number of tasks to workpool
* hex-mm: add proper checks for no-work in dyn.quant tasks
* hex-mm: convert all quantizers into a macro
* hex-mm: fix hvx-flat fallback to pass all MUL_MAT tests
* hex-mm: vectorize q8_1 quantizer
* hex-mm: improve fused ffn mm stride handling
* hex-mm: consistent use of n_threads and pipeline in kernel_params
* hexagon: minor formatting
* hex-mm: update MUL_MAT_ID kernel_param handling to make sure host/npu are in sync
* hvx-mm: go back to accumulating in fp32 in tiled hvx kernels, more accurate and same perf
* hvx-mm: unroll the loops and remove masking that is not needed for tiled accums
* hmx-mm: optimize activation processing (slit loops, some unrolling, etc)
* hmx-mm: minor optimization for output processing
* hex-mm: consistent use of uint32_t and size_t in mm kernels
* hex-mm: remove legacy restrictions for rows to be multiple of 256
* hexagon: replace sprintf with snprintf
* hex-mm: relax hardcoded nrows checks and rely on VTCM size requirements
* hexagon: minor alignment fix
* hexagon: fix trailing spaces
* hex-mm: relax padding from 256 to 128 (leftovers)
* hex-mm: remove redundant checks for weight align to 128
we always use 2D dma for the weights and align them properly
* hmx-mm: MUL_MAT_ID better work distribution between hvx threads and hmx tracing
* hex-mm: specialize per-token mmid activation handling
* hex-profile: update python scripts to handle kernel-params section in the logging output
* hex-mm: move n_prefetch (aka dma_depth) into kernel params and remove unused fields
* hex-trace: use easier to parse format, simply and fix post-proc scripts
* hmx-mm: relax 32 row limit for output processing which helps utilization
* hmx-mm: use start-chunk idx for tracing info
* hmx-mm: parameterize activation dma pipeline
* hexagon: add support for simple graph caching to avoid recomputing kernel-params
* hex-mm: remove left-over repack functions
* hex-mm: tighten n_prefetch asserts
* hex-mm: remove duplicate round/align_up helper
* hexagon: cleanup common header used in host/npu
* hexagon: update early wakeup threshold
* hmx-mm: define cost constants and update solver to assume that repacked ne[1] is padded to 32
* hmx-mm: make precompute_matmul a bit more readable (split into smaller functions, etc)
* hex-mm: remove n_threads constraint
* hex-mm: minor formatting updates
* hex-mm: remove obsolete profiling logs
* hex-mm: restore hardcode gate to refuse lm-head to avoid repacking that tensor
* vulkan: make SQR/SQRT/SIN/COS/CLAMP/LEAKY_RELU use unary.comp
* vulkan: make NORM support noncontig
* add noncontiguous row test cases for norm/l2_norm, handle this in the CPU backend and l2_norm.comp
* fix supports_op for cuda and webgpu
* server : improve message span logic
* cont : cast size_t to int32_t in comparisons
* server : create checkpoints before every user msg
* chat : remove \n in gemma4 delimiters
* chat : merge msg delimiter structs into one
* cont : reword comment
* cont : initialize tokens in delimiter
* cont : add server_tokens::get_raw_tokens() for mtmd
* cont : move message finding to server_tokens and skip mtmd tokens
* cont : update cohere2moe parser
* cont : increase min-step to 8192 and always produce a chkpt for last user message
* common/peg : refactor until gbnf grammar into an ac automaton
* cont : add a test with multiple strings
* cont : pad state with 0s so rules line up
* cont : clean up comments
* cont : use set everywhere
* cont : inline state num string padding
* cont : add a ref to PR
* cont : fix regression in server-tools.cpp
* arg: try fixing test-args-parser randomly fails
* return ref
* try triggering the workflow
* exception wrapper
* wip
* test
* test 2
* arg: guard win32 utf8 argv override
make_utf8_argv rebuilds argv from GetCommandLineW to fix utf8 handling of
non ascii arguments on windows. the override runs unconditionally inside
common_params_parse, so it also clobbers a programmatic argv passed by a
caller. test-arg-parser builds a synthetic argv but then sees the real
process command line instead, the model argument is never parsed, and the
assert that expects success aborts via fastfail (0xC0000409). this shows up
as a random failure in the openvino windows workflow.
only override argv when its length matches the caller argc, so the utf8
repair still applies to real binaries while a programmatic argv stays intact.
---------
Co-authored-by: Pascal <admin@serveurperso.com>
Piotr Wilkin