* vulkan: use coopmat for flash attention p*v matrix multiplication
* fix P loading issue
* fix barrier position
* remove reduction that is no longer needed
* move max thread reduction into loop
* remove osh padding
* add bounds checks and padding
* remove unused code
* fix shmem sizes, loop duration and accesses
* don't overwrite Qf, add new shared psh buffer instead
* add missing bounds checks
* use subgroup reductions
* optimize
* move bounds check, reduce barriers
* support other Bc values and other subgroup sizes
* remove D_split
* replace Of register array with shared memory Ofsh array
* parallelize HSV across the rowgroups
* go back to Of in registers, not shmem
* vectorize sfsh
* don't store entire K tile in shmem
* fixes
* load large k tiles to shmem on Nvidia
* adapt shared memory host check function to shader changes
* remove Bc 32 case
* remove unused variable
* fix missing mask reduction tmspsh barrier
* fix mask bounds check
* fix rowmax f16 under/overflow to inf
* fix flash_attn_cm2 BLOCK_SIZE preprocessor directives
* convert : yield Mamba2Model/GraniteMoeModel modify_tensors
This commit updates the `GraniteHybridModel` class' modify_tensors
function to properly delegate to `Mamba2Model.modify_tensors` and
`GraniteMoeModel.modify_tensors` using 'yield from' instead of 'return'.
The motivation for this is that modify_tensors is a generator function
(it uses 'yield from'), but the two calls above use return statements
but don't yield anything which means that the the caller of this
function will not receive any yielded values from it. And this causes
layer tensors to be silently dropped during conversion.
The syclcompat/math.hpp is not used anymore. The change that intrduced it was successfuly reverted (https://github.com/ggml-org/llama.cpp/pull/17826).
This include path will become obsolete and dropped in oneAPI 2026.0 effectively breaking ggml-sycl builds.
* undefined is treated as iterable (string/array) by filters
`tojson` is not a supported `undefined` filter
* add tests
* add sequence and iterable tests
keep it DRY and fix some types
Deduplication here relied on the fact that vulkan would return unique
UUID for different physical GPUs. It is at the moment not always the case.
On Mac Pro 2019 running Mac OS, with 2 Vega II Duo cards (so, 4 GPU total),
MotlenVK would assign same UUID to pairs of GPUs, unless they
are connected with Infinity Fabric.
See more details here: KhronosGroup/MoltenVK#2683.
The right way is to fix that in MoltenVK, but until it is fixed,
llama.cpp would only recognize 2 of 4 GPUs in such configuration.
The deduplication logic here is changed to only filter GPUs if UUID is
same but driver is different.
* sampling : remove sampling branching in output_reserve
This commit updates output_reserve in llama-context.cpp to always
allocate sampling buffers regardless of whether sampling is needed for
the current batch.
The motivation for this is to avoid reallocations and branching based on
the sampling requirements of the batch.
* Boilerplate for q6_K repack
* q6_K repack to q6_Kx8 implementation
Signed-off-by: Alberto Cabrera <alberto.cabrera@liquid.ai>
* q6_K generic gemv and gemm
* wip, gemm_q6_K 8x8
* Still WIP: loading of q8s, q6h and q6l
* first working version of q6_K gemm
* Moved q6 loads outside of sb block, Unrolled inner loop
* Replaced modulo with mask
* First implementation of GEMV
* ggml_vdotq_s32 -> vdotq_s32
* Reduce width of accumulators in q6_K gemv
* Bsums instead of calc bias. Preload scales to use vget_lane. Unroll.
* Reuse scales in GEMM (same GEMV opt)
* Added todos for bsum and different qh repack
* Arch fallback
* VSLIQ for merging qh adn ql
* Removed TODO, already tested
* Apply suggestions
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
* Removed unused import
---------
Signed-off-by: Alberto Cabrera <alberto.cabrera@liquid.ai>
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
* [CUDA] Reduce CPU-side stalls due to the CUDA command buffer being full
With pipeline parallelism, during prompt processing, the CPU-side CUDA command buffer gets full, stalling the CPU. Due to this, enough work doesn't get submitted to the GPU, causing bubbles in the GPU timeline.
Fix this by setting the CUDA environment variable CUDA_SCALE_LAUNCH_QUEUES to 4x to increase the command buffer size.
* Set the env variable in the CUDA backend registry allocation
* Add link to PR in code comment
* Remove warning logs and update documentation
* common : clarify HTTPS build options in error message
This commit updates the https error message to provide clearer
instructions for users who encounter the "HTTPS is not supported" error.
The motivation for this is that it might not be clear to users that only
one of these options are needed to enable HTTPS support.
The LLAMA_OPENSSL option is also added to the message to cover all
possible build configurations.
* clarify that OpenSSL is the default for HTTPS support
* opencl: flatten `q6_K` and add `kernel_mul_mv_q6_K_f32_flat`
* opencl: clean up
* opencl: refactor q6_K mv - put loop body in `block_q_6_K_dot_y_flat`
* opencl: tweak the workgroup size a bit
* opencl: output 4 values per subgroup for `kernel_mul_mv_q6_K_f32_flat`
* opencl: proper alignment for q6_K
* opencl: boundary handling for flattened q6_K mv
* opencl: rename q6_K mv kernel file
* opencl: put flattened q6_K mv in its own file
* opencl: use lower k in file name
* opencl: use K in variable names
* ggml-cpu: Use tiled FA for prompt-processing
the FA performance is gimped on CPU on long contexts because it essentially uses a vector kernel. This PR adds a tiled FA for PP. Perf tuning for tile sizes done on a AMD EPYC single-socket 64-c machine.
* fix out of bounds for mask
* skip rows where there are all masks
* skip tile if mask is inf
* store mask in worksize
* check inf tile earlier
* common : use two decimal places for float arg help messages
This commit updates the help messages for various command-line arguments
in arg.cpp to display floating-point default values with two decimal
places instead of one.
The motivation for this changes is that currently only having one decimal
place means that values generated using --help or llama-gen-docs will not
display the correct values.
For example, currently the value of top-p in tools/server/README.md is
`0.9`, but the default value is actually '0.95'. And running
llama-gen-docs does not update this value as it uses the output from the
help message, which shows only one decimal place, so the values look
like they are unchanged.
* docs : run llama-gen-docs to update docs
* graph : avoid branches between embedding and token inputs
* models : make deepstack graphs (e.g. Qwen3 VL) have constant topology
* ci : enable -DGGML_SCHED_NO_REALLOC=ON for server CI
* cont : pad token embeddings to n_embd_inp
Sigbjørn Skjæret
Ruben Ortlam
Sascha Rogmann
Daniel Bevenius
Patryk Kaminski
Oleksandr Kuvshynov
Ben Chen
Kevin Pouget
Alberto Cabrera Pérez
Georgi Gerganov
Nikhil Jain
Vishal Singh
David Lima
Johannes Gäßler
Gaurav Garg
shalinib-ibm
lhez
ccbinn
Aman Gupta
Molly Sophia
Jakkala Mahesh
Bartowski
Xuan-Son Nguyen
nullname
Neo Zhang