Skip to content

Releases: LongLeCE/llama.cpp

b6795

18 Oct 15:46
ee09828

Choose a tag to compare

HIP: fix GPU_TARGETS (#16642)

b6792

18 Oct 03:16
8138785

Choose a tag to compare

opencl: transposed gemm/gemv moe kernel with mxfp4,f32 (#16602)

* opencl: transposed gemm/gemv moe kernel with mxfp4,f32

* add restore kernel for moe transpose

* fix trailing whitespaces

* resolve compilation warnings

b6791

17 Oct 21:15
66b0dbc

Choose a tag to compare

llama-model: fix insonsistent ctxs <-> bufs order (#16581)

b6789

17 Oct 15:19
3d4e86b

Choose a tag to compare

vulkan: Add State Space Model (SSM) Operations Support (#16463)

* vulkan: implement SSM scan operation

Add State Space Model scan operation to the Vulkan backend.

Signed-off-by: Giuseppe Scrivano <gscrivan@redhat.com>

* vulkan: implement SSM conv operation

Add State Space Model conv operation to the Vulkan backend.

Signed-off-by: Giuseppe Scrivano <gscrivan@redhat.com>

---------

Signed-off-by: Giuseppe Scrivano <gscrivan@redhat.com>

b6787

17 Oct 09:15
ababae7

Choose a tag to compare

webui: reorganize settings layout (#16607)

* webui: reorganize settings layout

* chore: update webui build output

* fix: remove unused variable

* chore: update webui build output

b6783

17 Oct 03:11
ceff6bb

Choose a tag to compare

SYCL SET operator optimized for F32 tensors (#16350)

* SYCL/SET: implement operator + wire-up; docs/ops updates; element_wise & ggml-sycl changes

* sycl(SET): re-apply post-rebase; revert manual docs/ops.md; style cleanups

* move SET op to standalone file, GPU-only implementation

* Update SYCL SET operator for F32

* ci: fix editorconfig issues (LF endings, trailing spaces, final newline)

* fixed ggml-sycl.cpp

---------

Co-authored-by: Gitty Burstein <gitty@example.com>

b6782

16 Oct 21:24
1bb4f43

Choose a tag to compare

mtmd : support home-cooked Mistral Small Omni (#14928)

b6781

16 Oct 15:19
683fa6b

Choose a tag to compare

fix: added a normalization step for MathJax-style \[\] and \(\) delim…

b6779

16 Oct 09:17
7a50cf3

Choose a tag to compare

CANN: format code using .clang-format (#15863)

This commit applies .clang-format rules to all source files under the
ggml-cann directory to ensure consistent coding style and readability.
The .clang-format option `SortIncludes: false` has been set to disable
automatic reordering of include directives.
No functional changes are introduced.

Co-authored-by: hipudding <huafengchun@gmail.com>

b6774

15 Oct 22:07
466c191

Choose a tag to compare

cpu : add FLOOR, CEIL, ROUND and TRUNC unary operators (#16083)

* CPU: Add support for FLOOR,CEIL,ROUND and TRUNC unary operators

- Added the operators to unary op enum
- Implemented API functions
- Implemented forward and unary-op logic in CPU backend
- Updated ggml_get_n_tasks
- Updated operators names array and static_assert
- Updated docs and enabled automatic tests

* docs: add documentation for ggml_trunc and ggml_trunc_inplace in ggml.h

* chore: remove trailing whitespace from ggml.h

* Remove unresolved merge markers

* Apply review suggestions: cleanup formatting, enum order and leftover artifacts

* Regenerate ops.md using create_ops_docs.py