Skip to content

Tags: ggml-org/llama.cpp

Tags

b6140

Toggle b6140's commit message

Verified

This commit was created on GitHub.com and signed with GitHub’s verified signature.
HIP: disable sync warp shuffel operators from clr amd_warp_sync_funct…

…ions.h (#15273)

b6139

Toggle b6139's commit message

Verified

This commit was created on GitHub.com and signed with GitHub’s verified signature.
sycl: Fix and disable more configurations of mul_mat (#15151)

* sycl: Fix and disable more configurations of mul_mat

* Disable more configurations

b6138

Toggle b6138's commit message

Verified

This commit was created on GitHub.com and signed with GitHub’s verified signature.
opencl: allow mixed f16/f32 `add` (#15140)

b6137

Toggle b6137's commit message

Verified

This commit was created on GitHub.com and signed with GitHub’s verified signature.
CUDA cmake: add `-lineinfo` for easier debug (#15260)

b6136

Toggle b6136's commit message

Verified

This commit was created on GitHub.com and signed with GitHub’s verified signature.
CANN: GGML_OP_CPY optimization (#15070)

Signed-off-by: noemotiovon <757486878@qq.com>

b6135

Toggle b6135's commit message

Verified

This commit was created on GitHub.com and signed with GitHub’s verified signature.
musa: fix failures in test-backend-ops for mul_mat_id op (#15236)

* musa: fix failures in test-backend-ops for mul_mat_id op

Signed-off-by: Xiaodong Ye <xiaodong.ye@mthreads.com>

* Address review comments

Signed-off-by: Xiaodong Ye <xiaodong.ye@mthreads.com>

---------

Signed-off-by: Xiaodong Ye <xiaodong.ye@mthreads.com>

b6134

Toggle b6134's commit message

Verified

This commit was created on GitHub.com and signed with GitHub’s verified signature.
CANN: Add broadcast for softmax and FA (#15208)

* refactor softmax

* fix fa

* fix mask shape

* format

* add comments

* Remove whitespace

b6133

Toggle b6133's commit message

Verified

This commit was created on GitHub.com and signed with GitHub’s verified signature.
mtmd : Fix MinicpmV model converter and clip to avoid using hardcode. (

…#14750)

* Fix MinicpmV model converter and clip to avoid using hardcode.

* Code update for pr/14750

* Remove unused field, update script path in docs.

* Add version 5 for fallback code.

---------

Co-authored-by: lzhang <zhanglei@modelbest.cn>

b6132

Toggle b6132's commit message

Verified

This commit was created on GitHub.com and signed with GitHub’s verified signature.
chat : hotfix gpt-oss jinja raising an exception (#15243)

* chat : hotfix gpt-oss jinja raising an exception

* fix

b6131

Toggle b6131's commit message

Verified

This commit was created on GitHub.com and signed with GitHub’s verified signature.
server : allow specifying reasoning_format in HTTP request (#15238)