* hex-fa: clean up qf32/fp32 handling and stride handling
* hex-fa: fix corner case fp NAN issues that were cause bad output from gemma4 on v79
* hex-fa: vectorize leftover handling
* hex-fa: avoid HVX fallback during token gen HMX has more FP16 compute capacity
* hmx-mm: remove dead code
* hmx-mm: use fastdiv in x4x2 dequant
* hmx-mm: sandwich dequant and scatter to improve perf
* hmx-mm: fixed rebase conflicts
* hmx-mm: further improve weight dequant by doing early type dispatch and precomputing fastdiv
* hmx-mm: an even earlier dispatch for per-type dequant
* hmx-mm: dequant linear types like q4_0 and q4_1 without the LUTs
This is a bit faster than LUT.
* hex-cmake: one more tweak for lto
---------
Co-authored-by: Trivikram Reddy <tamarnat@qti.qualcomm.com>
* allow caching of ui elements in llama-server
* use fnv_hash
* Update tools/server/server-http.cpp
etag has to be set always
Co-authored-by: Xuan-Son Nguyen <thichthat@gmail.com>
---------
Co-authored-by: Xuan-Son Nguyen <thichthat@gmail.com>
* Updated vec.h/vec.cpp code to accumulate to F32 rather than F16
Change-Id: I0cb789347f2bf60ffaf9047319f727e788c825f8
Signed-off-by: Martin Klacer <martin.klacer@arm.com>
Co-authored-by: Milos Puzovic <Milos.Puzovic@arm.com>
* ci : separate CUDA windows workflow + fix names
* ci : rename workflow
* ci : prefix cache names with workflow name
* ci : rename build.yml -> build-cpu.yml
* ci : cache keys
* ci : fix windows cuda/hip concurrency of release workflow
* ci : fix apple cache names
* ci : add TODOs
* cont : keep just the last cache
* ci : update release concurrency to queue
* ci : move the release trigger to ubuntu-slim
* ci : hip add TODO
* cont : improve words
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
* OP_GATED_DELTA_NET impl
* add back lanes_per_column declaration
* removed has_subgroup_arithmetic and has_subgroup_clustered_reduce
* removed trailing spaces and fixes indentation. Hard coded subgroup size for Adreno and Intel. Return not supported when K>1 state snapshot
* support for K>1 state snapshot
* removed picky indent multiple of 4 fixes
* removed return that won\'t be executed
* hex-mm: add support for Q4_1 matmul/matvec, hvx-only for now
* hmx-mm: add support for Q4_1
* hex-mm: use Q8_1 dynamic quantization to avoid having to compute sums in the vec_dot
* hexagon: fix repack scratch buffer overflow
* hex-mm: fix Q4_1 repack buffer sizing
* hexagon: flip the build order for mm and fa (seems to help LTO)
* hex-mm: add vec_dot 4x1s and minor HMX cleanup after adding Q4_1
* hex-mm: fix fp16 vec_dot fallback to 2x1 and another issue that could cause incorrect output
* hexagon: resurrect early-wake and add support for polling for op-batch completions
With Q4_1 ggml-hexagon now claims pretty much the entire graphs which gives the CPU more time to chilax.
This is a good thing! But it does add extra latency for the pure benchmark runs.
Early wakeup helps recover the latency a bit in the normals runs and op-batch polling is just for benchmarking.
---------
Co-authored-by: Todor Boinovski <todorb@qti.qualcomm.com>
* vulkan: Switch MUL_MAT_VEC to 4 K per iteration for F16/32
Against mesa git, this shows a 4.8% performance improvement for
tg128 on Qwen3.5-9B:BF16 on Intel BMG.
Note that this breaks some tests until the last commit which fixes
OOB A reads.
* vulkan: Use aligned loads in mul_mat_vec when available
Against mesa git, this shows a 3.3% performance improvement for
tg128 on Qwen3.5-9B:BF16 on Intel BMG.
* Make explicit that `num_rows` is <= `NUM_ROWS` in mul_mat_vec
Mesa's UUB logic can't see through conditionals, limiting its
ability to understand the bounds on the `num_rows` field in the
cleanup run. Making it explicit that `num_rows` is, indeed, always
<= `NUM_ROWS` helps mesa make slightly better codegen.
Against mesa git, this currently shows a 1% performance improvement
in tg128 on Qwen3.5-9B:BF16 on Intel BMG.
* vulkan: Fix OOB A reads in MUL_MAT_VEC for odd sizes
There was a TODO to fix the OOB reads from the A matrix which we do
here.
It is within performance noise (+<0.1%) in tg128 for
Qwen3.5-9B:BF16 on Intel BMG.
* feat: extend repeat op for vulkan
* feat: add repeat_f16 vulkan pipeline
* fix: ensure same dst and src types
* fix: use type_size instead of data types
* fix: use int16 and int32 for repeat shader op
* chore: rename repeat_f* to repeat_i*
* chore: rename repeat vulkan pipelines
* ci : server windows set build type explicitly
* cont : try windows-2025
* ci : use llvm
* cont : use ninja
* cont : fix shell
* ci : set number of jobs correctly
* ci : fix windows with vulkan ccache by using llvm
* ci : server ccache only on master
* ocd : fix job names
[no release]
* ci : fix undefined sanitizer build to use Debug build type only
* ci : ccache the server builds
* cont : remove ui dependency + reuse ccache for both ubuntu jobs
* tmp : force ccache save
* Revert "tmp : force ccache save"
This reverts commit a857b03a10b1304d456129a017e0e46b185618ee.
* cont : no need for node.js
Add minicpm5 pre-tokenizer hash via convert_hf_to_gguf_update.py and
implement hardcoded regex handling in llama-vocab.cpp, consistent with
other BPE pre-tokenizers.
Co-authored-by: zhangtao <zhangtao2@modelbest.cn>
* ggml-zendnn: fixed naming of matmul function
* ggml-zendnn: fixed naming of mul_mat_id function
* ggml-zendnn: fixed print in mul_mat_id
---------
Co-authored-by: plotnikov.v10 <plotnikov.v10@wb.ru>
* ci : move [no release] check to dedicated check_release job
Move the workflow-level \`if\` condition that skips builds when the commit
message contains \`[no release]\` into a lightweight \`check_release\` job.
All build jobs now depend on it via \`needs\` and check its output.
This ensures the skip logic is evaluated at the job level rather than at
the workflow level, which is the recommended approach for conditional jobs.
Assisted-by: llama.cpp:local pi
* cont : use `fast` runner
* ci : skip release workflow on master when commit message contains [no release]
Assisted-by: llama.cpp:local pi
* ci : restrict sanitizer builds to x86_64 + fix build type
the spark is apparently too slow for some reason
* tests : fix undefined warning
[no ci]
* vulkan: add CONV_SHAPE_64x128 for medium-K conv2d
* vulkan: skip conv2d bounds checks when shapes align with tile sizes
* vulkan: use WG_SIZE=128 for CONV_SHAPE_64x32 conv2d
* vulkan: stage cm2 conv2d accumulator through shmem before global store
* vulkan: add coopmat1 conv2d path
* fallback when using too much shared memory. clean up comments
* Require 16x16x16 and subgroup size 32 or 64
* check whether shared memory is sufficient before overwriting conv2d params with coopmat1 values
* hexagon: add support for CONCAT with optimized concat_2d_transposed
qwen3.5 models are quite heavy on the CONCAT with large and transposed src1.
* hex-concat: use fastdiv in generic version
* hex-concat: make checks for transposed a bit more readable
* hex-concat: reoder dma ops for better pipelining
* hex-cont/cpy: optimize CPY and CONT ops
The primary change is to avoid scalar divs in the inner loops.
We were calling hvx_copy_uu(... type_size) where type_size is non a constexpr.
This causes runtime divs by that value which is normally just 4 or 2 (f32/f16).
* hex-get-rows: optimize GET_ROWS for large rows
We now use DMA for larger rows and also split them into chunks to improve perf for Qwen3.5 and other models
that do lots of GET_ROWS with huge (2MB+ rows).
Also bump the DMA queue depth now that we can take advantage of it.
* hex-concat: unroll the inner loops of concat_2d
* hex-concat: more updates to concat_2d to improve perf a bit further
* hex-cpy: fixed n_rows per thread checks in the copy ops
* hmx-fa: fix alignment issues while computing dma sizes
* hex-set-rows: add early returns for idle threads
* hvx-rope: minor optimization to replace loops with fastdiv logic
* hex-rope: replace scalar tail processing with HVX
* hex-rope: optimize rope cache init with HVX
Add hvx-utils sin/cos helpers that use an aprox method (similar to rsqrt, inverse, etc)
Use the helpers to optimize ROPE.
Create a pool of N threads that grab a chunk of up to 100 tests at a time to
iterate through. The number of tests at a time decreases as fewer remain.
Each thread uses its own dev and cpu backend, and set_n_threads_fn is not
called on the cpu backend.
Fix some TSAN issues that arose:
- In init_tensor_uniform, don't use static vector of generators.
- Replace gmtime with versions that don't use a global variable.
- Mutex calls to print_test_result.
* initial talkie support, coherent
* reorder to follow convention
* absorb inverse rope
* stop folding scalars to improve quantization
* use broadcasting instead of duplication
* style cleanup
* add scaling support to LoraTorchTensor; use that path in conversion
* use layer_out_scale instead of embd_skip_scale
* ggml-webgpu: Add MMVQ path for Q4/Q8/Q2_K/Q4_K
* Fix to editorconfig checking pass
* Remove mul-mat-legacy pipeline
* Fix to use vendor name as is and add dot_product/vendor to shader_lib_ctx
* Only run webgpu CI on my fork
* Add webgpu only workflow
* refactor batch_compute_passes to a per-thread variable, and submit individual passes when it is set to false and no GPU profiling is enabled
* restore build.yml
* ci : disable SYCL f16 builds
* ci : extract android and hip into separate workflows
* ci : move webgpu to separate workflow
* ci : move the rpc to a separate workflow
* ci : extract s309x and ppcl jobs
* ci : extract opencl job into a separate workflow
ffn_latent_down/up are declared GGML_OP_MUL in LLM_TENSOR_INFOS but
nemotron-h feeds them through ggml_mul_mat. The loader buft probe asks
the backend about the declared op, so it tested an elementwise MUL on a
q8_0 weight. That used to return true unconditionally and the weight
stayed on GPU by luck. Once supports_op told the truth, the probe got a
no and the loader pushed the weight and its matmul to CPU, splitting the
graph. Tagging it MUL_MAT asks the real question, the math is unchanged.
Verified on Nemotron 3 Super 120B Q5_K_M: from 64.9 back to 103.22 t/s.
* Refactored Compressed Tensors NVFP4 support for new base.py
* Support compressed-tensors NVFP4 conversion
* Moved Qwen MTP remap into filter_tensors
* simplify
* pathlib no longer used
---------
Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>
* TP: fix ggml context size calculation, memory leak
* move split state cache back into the context
* revert to constant ggml context size for cgraphs
* increase headroom for statically allocated tensors
* remove obsolete include
* ggml: implement `gguf_init_from_buffer`
* test: `gguf_init_from_buffer`
* fix: memory breakdown for a model loaded with `no_alloc` from a file is consistent with being loaded from a buffer
* fix: use `GGML_UNUSED`
Co-authored-by: Copilot <copilot@github.com>
* fix: remove `total_size` from `gguf_reader`
* fix: file offset calculation, rename `offset` to `data_offset`
Co-authored-by: Copilot <copilot@github.com>
* refactor: extract model loader bug fixes to another PR
* feat: add `gguf_init_from_callback`
* fix: always require a max expected size
* fix: change `gguf_reader_callback_t`'s `output` type to `void *`, change `max_expected_size` and offsets to `uint64_t`
* fix: harden against offset overflow in buffer read
* fix: remove seek behavior from the callback
* feat: `max_chunk_read == 0` means `SIZE_MAX`
* fix: seeking in a gguf file with no tensors
---------
Co-authored-by: Copilot <copilot@github.com>
* fix(action): update SpacemiT toolchain URL and version
Change-Id: If4cc1c738a855274103f8c3ad52daa33528acd0c
* fix(action): add -L flag to curl command for URL redirection
Change-Id: I9b6c37390f0c7a733a36308c8fb53d22d234ab06
- Use OpenMP to parallelize iq2xs_init_impl and iq3xs_init_impl.
- Move the OpenMP detection from ggml-cpu to ggml-base.
- Update OpenMP dependencies in ggml-config.cmake.in.
* common : add common_chat_split_by_role
* cont : fix spans to reach end of message
* server: fix checkpoints creation
- extract message_spans from chat templates
- find the prompt token position before the latest user message
- split prompt batching at that position
- create a context checkpoint before the latest user input
- avoid periodic mid-prompt checkpoints when that position is known
- handle multimodal prompts when mapping text/template positions to server prompt tokens
- add --checkpoint-min-step to control minimum spacing between checkpoints
* cont : clean-up
* Support autoparser detection for message barriers
* server: fix message span delimiter and update docs
---------
Co-authored-by: Alde Rojas <hello@alde.dev>
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
Co-authored-by: Piotr Wilkin <piotr.wilkin@syndatis.com>
* ci : remove tag from build-self-hosted.yml
* ci : slim -> self-hosted
* ci : prevent heavy CPU jobs from running on fast runners
* ci : prevent cmake pkg to run on dedicated fast runners
* ci : try to bump 3.11 -> 3.13
* ci : move lint back to 3.11
* ci : back to 3.11
* ci : add comment about UI jobs
* ci : move python requirements check to CPU runners
this job is a bit slow for a dedicated "fast" runner
* ci : add self-hosted ui workflow
* ci : fix UI naming
* tmp to check if arm64 fast is compatible with all jobs
* revert last commit
* requirements: relax torch~=2.6.0 to torch>=2.6.0 for convert_hf_to_gguf
The ~=2.6.0 operator resolves to >=2.6.0, <2.7.0, which fails on
PyPI for platform/CPython combinations where 2.6.x is not present.
The accompanying comment already says 'PyTorch 2.6.0 or later', so
the looser >=2.6.0 matches the documented intent and unblocks
pip install -r requirements/requirements-convert_hf_to_gguf.txt.
Fixes#23408
* requirements: bump torch floor to 2.11.0 per maintainer
* requirements: pin torch to ==2.11.0 per project policy
* requirements: pin mtmd torch and torchvision to 2.11.0/0.26.0 per project policy
* requirements: suppress check_requirements pin warning on mtmd
The check_requirements script flags '==' on lines in files matched by
*/**/requirements*.txt. Append the documented suppression comment to the
pinned torch and torchvision lines (and to the s390x platform marker lines)
so the check passes while keeping the pins required by project policy.
* ty: silence Tensor/Module union check on model[0].auto_model
With torch 2.11.0 stubs, nn.Sequential.__getitem__ now returns
Tensor | Module rather than Module, so model[0].auto_model fails ty
on the SentenceTransformer code path. The runtime behavior is
unchanged because SentenceTransformer always wraps a Module at
index 0. Adding a targeted unresolved-attribute ignore keeps the
type-check green without altering behavior. A follow-up issue
tracks typing the variable explicitly.
- change `k_copy_src1_to_contiguous` so that uses a precomputed contiguous mapping where all rows "owned" by an expert are in one slice with a know starts and ends
- switch the `O(n_as * n_routed_rows)` contraption to a counting sort-based procedure with `O(n_as + n_routed_rows)` complexity
* SYCL: add BF16 to DMMV kernel path for ~4x token generation speedup
BF16 models had no dedicated token generation kernel — they fell through
to the generic full-GEMM path, resulting in ~14% memory bandwidth
utilization on Intel Arc GPUs. This adds BF16 support to the DMMV
(dequantize mul-mat-vec) path, matching the existing F16 implementation.
Fixes#20478
* SYCL: fix BF16 DMMV out-of-bounds when ncols % 64 != 0
The qk=1 kernel (used for F16 and BF16) iterates with stride
2*GGML_SYCL_DMMV_X (= 64 on Intel targets where WARP_SIZE=16). When
ncols is a multiple of DMMV_X (32) but not of 2*DMMV_X (64), the last
warp iteration accesses elements at col >= ncols, producing NaN for the
final row and wrong values for interior rows.
Fix: tighten can_use_dequantize_mul_mat_vec to require ne[0] %
(2*DMMV_X) == 0 for F16/BF16 types, and update the ASSERT in the BF16
launcher to match. Quantized types use block-structured kernels with
different access patterns and keep the existing DMMV_X check.
Verified: test-backend-ops MUL_MAT passes 913/913 on Intel Arc Pro B70.
Previously failing: m=128/129 n=1 k=1056 cases (NaN and ERR > 0.0005).
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
---------
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
