Skip to content

Actions: ggml-org/llama.cpp

Actions

EditorConfig Checker

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
editorconfig.yml
15,073 workflow runs
15,073 workflow runs

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

opencl: add fastdiv and use it in set_rows, ported from cuda EditorConfig Checker #33921: Pull request #17090 opened by lhez
59m 39s qualcomm:lh/fastdiv
qualcomm:lh/fastdiv
59m 39s
CUDA: fix MMQ stream-k fixup ne1 indices EditorConfig Checker #33920: Pull request #17089 opened by JohannesGaessler
57m 11s JohannesGaessler:cuda-fix-mmq-moe-6
JohannesGaessler:cuda-fix-mmq-moe-6
57m 11s
Add ops needed for new hybrid models: SOFTPLUS, EXPM1, TRI, SOLVE_TRI, CUMSUM EditorConfig Checker #33919: Pull request #17063 synchronize by pwilkin
1h 36m 45s pwilkin:hybrid_ops
pwilkin:hybrid_ops
1h 36m 45s
Add ops needed for new hybrid models: SOFTPLUS, EXPM1, TRI, SOLVE_TRI, CUMSUM EditorConfig Checker #33918: Pull request #17063 synchronize by pwilkin
15s pwilkin:hybrid_ops
pwilkin:hybrid_ops
15s
server/public_simplechat alternate web client ui with 0 setup builtin tool calling++, reasoning - refactored, SysDateTime, rename pdftext EditorConfig Checker #33917: Pull request #17038 synchronize by hanishkvc
2h 9m 54s hanishkvc:hkvc_server_simplechat_toolcalling_v0450
hanishkvc:hkvc_server_simplechat_toolcalling_v0450
2h 9m 54s
vulkan : refactor buffer handling in vk_op_f32 (#16840) EditorConfig Checker #33916: Commit ac76d36 pushed by 0cc4m
1h 53m 3s master
master
1h 53m 3s
CUDA: fix should_use_mmvf for ne11 == 1 (#17085) EditorConfig Checker #33915: Commit 6515610 pushed by JohannesGaessler
1h 46m 38s master
master
1h 46m 38s
Vulkan: MMVQ Integer Dot K-Quant and MUL_MAT_ID support EditorConfig Checker #33914: Pull request #16900 synchronize by 0cc4m
1h 45m 24s 0cc4m/vulkan-mmq-dp4a-vec-k-quants
0cc4m/vulkan-mmq-dp4a-vec-k-quants
1h 45m 24s
bench : cache the llama_context state at computed depth (#16944) EditorConfig Checker #33913: Commit 7956bb4 pushed by ggerganov
1h 26m 52s master
master
1h 26m 52s
metal : enable tensor API for A19 EditorConfig Checker #33912: Pull request #17087 opened by ggerganov
1h 14m 51s gg/metal-tensor-a19
gg/metal-tensor-a19
1h 14m 51s
hparams : add n_embd_inp() to support extended embed (#16928) EditorConfig Checker #33911: Commit 9008027 pushed by CISC
53m 32s master
master
53m 32s
bench : cache the llama_context state at computed depth EditorConfig Checker #33910: Pull request #16944 synchronize by ggerganov
45m 21s gg/context-skip-compute
gg/context-skip-compute
45m 21s
kv-cache : pad the cache size to 256 for performance (#17046) EditorConfig Checker #33909: Commit 16bcc12 pushed by ggerganov
1h 6m 10s master
master
1h 6m 10s
cmake: add option to build and link BoringSSL EditorConfig Checker #33908: Pull request #17062 synchronize by angt
59m 1s angt:cmake-add-option-to-build-and-link-boringssl
angt:cmake-add-option-to-build-and-link-boringssl
59m 1s
CUDA: fix should_use_mmvf for ne11 == 1 EditorConfig Checker #33907: Pull request #17085 synchronize by JohannesGaessler
1h 27m 51s JohannesGaessler:cuda-fix-should_use_mmvf
JohannesGaessler:cuda-fix-should_use_mmvf
1h 27m 51s
CUDA: fix should_use_mmvf for ne11 == 1 EditorConfig Checker #33906: Pull request #17085 synchronize by JohannesGaessler
3m 13s JohannesGaessler:cuda-fix-should_use_mmvf
JohannesGaessler:cuda-fix-should_use_mmvf
3m 13s
CUDA: fix should_use_mmvf for ne11 == 1 EditorConfig Checker #33905: Pull request #17085 synchronize by JohannesGaessler
12m 28s JohannesGaessler:cuda-fix-should_use_mmvf
JohannesGaessler:cuda-fix-should_use_mmvf
12m 28s
kv-cache : pad the cache size to 256 for performance EditorConfig Checker #33904: Pull request #17046 synchronize by ggerganov
57m 37s gg/iswa-pad-256
gg/iswa-pad-256
57m 37s
ggml-cpu : inspect -march and -mcpu to found the CPU EditorConfig Checker #33903: Pull request #16333 synchronize by angt
30m 18s angt:inspect-march-and-mcpu-to-found-the-cpu
angt:inspect-march-and-mcpu-to-found-the-cpu
30m 18s
CUDA: fix should_use_mmvf for ne11 == 1 EditorConfig Checker #33902: Pull request #17085 opened by JohannesGaessler
8m 12s JohannesGaessler:cuda-fix-should_use_mmvf
JohannesGaessler:cuda-fix-should_use_mmvf
8m 12s
Revert "ggml-cpu: detect correct cpu flags for arm64 (#16229) (#16239… EditorConfig Checker #33901: Commit 9eb9a13 pushed by ggerganov
29m 20s master
master
29m 20s
ggml-cpu : inspect -march and -mcpu to found the CPU EditorConfig Checker #33900: Pull request #16333 synchronize by angt
7m 27s angt:inspect-march-and-mcpu-to-found-the-cpu
angt:inspect-march-and-mcpu-to-found-the-cpu
7m 27s
Revert "ggml-cpu: detect correct cpu flags for arm64 (#16229) (#16239)" EditorConfig Checker #33899: Pull request #17084 opened by angt
25m 21s angt:revert-ggml-cpu-detect-correct-cpu-flags-for-arm64-16229-16239
angt:revert-ggml-cpu-detect-correct-cpu-flags-for-arm64-16229-16239
25m 21s
kv-cache : pad the cache size to 256 for performance EditorConfig Checker #33898: Pull request #17046 synchronize by ggerganov
13m 50s gg/iswa-pad-256
gg/iswa-pad-256
13m 50s
ggml-cpu: detect correct cpu flags for arm64 (#16229) (#16239) EditorConfig Checker #33897: Commit 7c23f3f pushed by slaren
17m 59s master
master
17m 59s
ProTip! You can narrow down the results and go further in time using created:<2025-11-07 or the other filters available.