* server : fix image blocks in tool_result being dropped during Anthropic→OpenAI conversion
server_chat_convert_anthropic_to_oai() silently discarded image blocks
inside Anthropic tool_result content. This broke multimodal tool outputs
(e.g. a tool that returns an image) because the model never received the
image.
When tool_result contains image blocks, convert them to OpenAI
multimodal content parts (text + image_url array). Plain-text results
remain simple strings for backwards compatibility.
* server : add test for image blocks in Anthropic tool_result conversion
If a Cuda device has no or limited available memory, the actual call
to cudaMemGetInfo() itself can cause a fatal crash due to a cuda out
of memory error (there is not enough memory to actually query memory)
This causes an issue because we query memory for all devices at
startup even if the user isn't trying to use the device for inference.
Fix this by making the error non-fatal and assigning zero total/free
memory to the device. This will have the downstream effect of the fit
algorithm not trying to put any layers on it, which is desired outcome
vs hard crashing.
this also prevents crashes in cuda enabled builds when user explicitly
passes '-dev none'
* [Vulkan] Fixes llama-cli breaking over longer promts sizes
The llama-cli was breaking for longer promts sizes for q4_0 quantized networks. Causing due to insufficient shared memory.
* Removed the un-used Adreno device
* Updated matmul for small pipeline.
* server: accept null sampling params
Extend the schema validation to treat a null value as absent, so
clients can send null on nullable params (temperature, top_p, ...)
to request the server default. This matches the OpenAI spec and the
json_value convention used elsewhere.
Add has_field() to skip null in the field eval guards.
* has_field -> has_value
llama_meta_device_get_split_state() recompiled 29 std::regex on every call.
In -sm tensor mode the callback runs once per tensor per token, so this
dominated the decode thread in profiling. Mark them static const so they are
compiled once. Kept inside the function (local statics are thread-safe since
C++11). Patterns are literal and stateless, so behavior is unchanged.
* hex-sort: add efficient bitomic sort in hvx regs up to 1024 elements
* hex-sort: fix inverted vrors
* hex-sort: specialize sort functions for the common cases
* hex-sort: add tracing and local context
* mtmd: deepseek-ocr v1 multi-tile dynamic resolution + unified image-preprocessors for both versions (ds-ocr v1 and v2)
* remove hacky API
* fuse row into a long image
* almost working
* adapt to new preprocessor api
* rm debugging printf
* improve
* mtmd: dsocr-tiles fixes (#25481)
* ds-ocr img-preproc fuse_row tile-drop fix for multi rows and columns images
* mtmd drop the duplicate redundant img_end
* deepseekocr graph simplify CLS broadcast cleanup
* test-deepseek-ocr: relax v1 single-view tolerance; drop trailing prompt space; make DRY opt-in and n_predict model-specific (#25486)
---------
Co-authored-by: Saba Fallah <10401143+sfallah@users.noreply.github.com>
Co-authored-by: Saba Fallah <sabafallah@gmail.com>
* llama-cli: fix crash on wrong server base url by catching exceptions and graceful exit
* review: leaner catch group: json error and standard exception
downloadConversation serialized activeMessages, the root -> currNode
path, so exporting a conversation with edited or regenerated messages
dropped every alternate version and kept only the selected one.
Fetch the whole message tree via getConversationMessages so the export
carries all message versions, matching the multi-conversation export
path which already did this. Keep the active conversation as the header
source to preserve an up-to-date currNode.
Forks are separate conversations, each with its own convId, and are
exported on their own.
* llama : make all KQ masks (except the lightning indexer one) f16 if FA is used and remove zero attention bias in DeepSeek V4
* llama : remove dead code that repeats unified raw_k cache for each stream in DeepSeek V4 - no longer needed as raw_k is always non-unified.
---------
Co-authored-by: Stanisław Szymczyk <sszymczy@gmail.com>
* ggml : process data in smaller chunks in CUDA ggml_top_k() implementation to reduce temporary buffers memory usage
* ggml : allocate tmp_dst only only once before the loop
* chore : whitespaces
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
* ggml : use chunked processing in both CUDA CUB top-k and argsort implementations
* chore : separate argsort_f32_i32_cuda_bitonic() call from return statement
Co-authored-by: Johannes Gäßler <johannesg@5d6.de>
* chore : replace ternary operators with min/max
---------
Co-authored-by: Stanisław Szymczyk <sszymczy@gmail.com>
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
Co-authored-by: Johannes Gäßler <johannesg@5d6.de>
A model whose chat template parses at init but fails parser generation
at apply time (e.g. uses {% call %}) throws std::invalid_argument from
common_chat_templates_support_enable_thinking(), which ran outside the
try/catch guarding common_chat_templates_init(). The throw was uncaught
and llama-cli aborted (SIGABRT) instead of failing to load. Moved the
probe inside that try/catch so an apply-time error fails load the same
way an init parse error does.
Signed-off-by: Jesse LaRose <jesse@taey.ai>
* meta: add hard emphasis on agents not writing descriptions/comments
Add a block in AGENTS.md to emphasize that agents are forbidden, under any circumstances, to post comments or pull request descriptions on behalf of the user.
* Add example
* Move examples to examples
* White space
* 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>
CUDA is compiled with fast math and AMD/HIP is not — this flag lets AMD use fast math too.
We can't use -ffast-math: it implies -ffinite-math-only, which won't compile (ggml uses INFINITY for masking) and produces NaNs. -funsafe-math-optimizations gives the speedup without the NaN problems.
Co-authored-by: Mark Caldwell <mark@cloudhands.ai>
* cuda: fix snake fusion type predicate, a and inv_b are F32
The matcher required a->type == x->type while launch_snake reads both
as const float *, matching the CPU and Metal contract where a and inv_b
stay F32. F16/BF16 chains never fused and fell back to the naive path,
and a hypothetical all F16 chain would have read F16 bits as float.
Aligns the predicate and the comment with ggml-cpu.c
* cuda: reject snake fusion on non-contiguous operands
The kernel reads x[idx] and a[c] / inv_b[c] linearly, so a
non-contiguous view passing the matcher would silently read wrong data.
Mirror the contiguity guard already present in the CPU, Vulkan and
Metal matchers.
* hexagon: add VISION RoPE support
* hexagon: support RoPE on strided half-dim views for all modes
* hex-rope: decouple src0 DMA copy size from row stride
* hex-rope: support non-contiguous dst for RoPE
* hex-rope: fix dst spad pitch for non-contiguous dst
* opencl: fix garbled output for Q6_K weights with ne01 % 128 != 0 on Adreno
Observed with granite-3.1-3b-a800m-instruct, whose vocab is an odd number.
Route Q6_K dense mul_mat with ne01 % 128 != 0 off the noshuffle path:
decode (ne1==1) uses the correct flat GEMV and the matching GEMM (ne1>1)
falls back to CPU (the flat convert has no verified small-batch GEMM kernel
for these shapes). All standard hidden/FFN/vocab dims are multiples of 128
and keep the noshuffle path.
* opencl: reserve alignment slack for the SOA subbuffer carve in alloc size
set_tensor carves quantized weights into per-component subbuffers (d/q,
ql/qh/s/d, ...) whose origins are each rounded up to the device base
address alignment. When a component's size is not a multiple of the
alignment, the carve extends past ggml_nbytes(tensor) and the last
subbuffer overlaps the next tensor in the pool -- e.g. q6_K [1536, 49155]:
size_s = 49155*96 ends 32 bytes past a 128-byte boundary, so the d
subbuffer ends 96 bytes past the tensor's allocation, and whichever of the
two neighboring tensors is uploaded last silently corrupts the other (here:
the last vocab rows' block scales). This affects any quant type whose
component sizes can be misaligned, on any shape with ne01 not a multiple of
the alignment granularity; standard power-of-two dims are unaffected.
Implement get_alloc_size for the OpenCL buffer type and reserve the
worst-case carve slack (4 aligned gaps; 5 components max, q5_K) for
quantized tensors. Costs at most 512 bytes per quantized tensor at the
observed 128-byte alignment.
* opencl: use lm based q6_k mm when ne1 is not multiple of 128
---------
Co-authored-by: Li He <lih@qti.qualcomm.com>
* opencl: ragged-tile MoE prefill GEMM (skip padded expert tiles)
The MoE prefill GEMM groups tokens into TILESIZE_N=32 per-expert tiles; at low
tokens-per-expert most tiles are mostly padding. When a tile's upper 16 slots
are all padding (router index 0xFFFFFFFF), skip the second dotx16_reduce8 half.
Numerically identical (skipped lanes are padding). Applied to all eight *_f32_ns
MoE GEMMs; default on, opt out with GGML_OPENCL_MOE_RAGGED_FP16=0.
* opencl: quarter-granularity ragged MoE tile-skip (8-col skip-groups)
Replace the two half-tile dotx16_reduce8 calls in the 8 *_f32_ns MoE GEMMs with
four dotx8_reduce4 (8-column) calls, skipping each empty trailing skip-group
independently. Padding is always trailing, so the kernel rounds the valid count
up to the skip granularity and skips fully-padding groups. Byte-identical to the
non-skipped path. New env GGML_OPENCL_MOE_RAGGED_GRAN={8,16,32} (quarter/half/
off); default quarter.
* opencl: move ragged moe env var in cl_init
---------
Co-authored-by: Li He <lih@qti.qualcomm.com>
* hex-fa: refactor kernel param compute to use common layout builder
* hmx: add explicit compiler barriers to make hmx funcs more robust
* hex-vtcm: more generic vtcm layout builder for mm and flash-attn kernels
* hex-hmx: unroll inner kernels
* hex-hmx: use inline asm instead of intrinsics to avoid compiler issues
* hex-hmx: define inline asm macros and simplify code
* hex-hmx: replace leftover intrinsics
* hmx-fa: minor cleanup for hmx asm
* hmx-mm: move per-task stucts out of the kernels header
* hmx-mm: simplify core_dot_chunk
* hmx-mm: simplify inner loops that call hmx instructions
* hmx-mm: proper instrumentation for activation prep work for dma pipelined version
* hmx-mm: update a-prep loop for better prefetch
* hex-vtcm: improved vtcm layout alloc for mm to support overlapping areas
* hmx-mm: reduce the number of act fetch tows to 4 for now, going larger doesnt help here
* hex-hmx: always use hmx-queue in all modes
* hmx-mm: update comments and minor formatting
* hmx-mm: further improve synchro fallback path to prefetch the weights earlier
* hex-fa: further pipeline improvements (earlier prefetch)
* hmx-mm: cleanup dma pipelines to use dst cached in the queue
* hmx-fa: minor cleanup and opts for fa dma pipelines
* hmx-fa: optimize q-prep stage with dma and unrolling
* hmx-fa: use o_tile size from layout instead of computing it
* hmx-mm: cleanup types and size handling
* hmx-mm: replace divs with fastdiv in qprep loops
* hmx-fa: minor update/formatting to q_tile handling
* hmx-fa: cleanup the layout to avoid overpadding
* hmx-fa: simplified and improved cost mode for hmx fa solver that uses vtcm layout funcs
* hmx-queue: add support queue wakeup and make suspend async to avoid hmx-lock latency
* hex-hmx: move queue wakeup / suspend to the op-batch level
* hex-threads: add hybrid polling to workpool
* hex-mm: fix trailing spaces
