Skip to content

Actions: ggml-org/llama.cpp

Actions

All workflows

Actions

Loading...
Loading

Showing runs from all workflows
51,206 workflow run results
51,206 workflow run results

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

vulkan: Support ne[3]>1 in noncontig matrix-vector multiply Pull Request Labeler #14244: Pull request #15015 opened by jeffbolznv
12s
12s
CUDA: fix MMQ nwarps for AMD with warp_size==32 CI #25596: Pull request #15014 opened by JohannesGaessler
58m 33s JohannesGaessler:cuda-mmq-fix-nwarps
JohannesGaessler:cuda-mmq-fix-nwarps
58m 33s
CUDA: fix MMQ nwarps for AMD with warp_size==32 EditorConfig Checker #28735: Pull request #15014 opened by JohannesGaessler
19s JohannesGaessler:cuda-mmq-fix-nwarps
JohannesGaessler:cuda-mmq-fix-nwarps
19s
CUDA: fix MMQ nwarps for AMD with warp_size==32 Pull Request Labeler #14243: Pull request #15014 opened by JohannesGaessler
10s
10s
vendor : update vendored copy of google/minja (#15011) Release #587: Commit c76b420 pushed by CISC
19m 43s master
master
19m 43s
vendor : update vendored copy of google/minja (#15011) EditorConfig Checker #28734: Commit c76b420 pushed by CISC
20s master
master
20s
vendor : update vendored copy of google/minja (#15011) Server #17002: Commit c76b420 pushed by CISC
23m 42s master
master
23m 42s
vendor : update vendored copy of google/minja (#15011) CI #25595: Commit c76b420 pushed by CISC
55m 20s master
master
55m 20s
vendor : update vendored copy of google/minja CI #25594: Pull request #15011 synchronize by l-austenfeld
1h 12m 52s l-austenfeld:master
l-austenfeld:master
1h 12m 52s
vendor : update vendored copy of google/minja Server #17001: Pull request #15011 synchronize by l-austenfeld
13m 18s l-austenfeld:master
l-austenfeld:master
13m 18s
vendor : update vendored copy of google/minja EditorConfig Checker #28733: Pull request #15011 synchronize by l-austenfeld
24s l-austenfeld:master
l-austenfeld:master
24s
vendor : update vendored copy of google/minja Pull Request Labeler #14242: Pull request #15011 synchronize by l-austenfeld
12s
12s
vendor : update vendored copy of google/minja EditorConfig Checker #28732: Pull request #15011 synchronize by l-austenfeld
23s l-austenfeld:master
l-austenfeld:master
23s
vendor : update vendored copy of google/minja CI #25593: Pull request #15011 synchronize by l-austenfeld
1m 20s l-austenfeld:master
l-austenfeld:master
1m 20s
vendor : update vendored copy of google/minja Server #17000: Pull request #15011 synchronize by l-austenfeld
1m 24s l-austenfeld:master
l-austenfeld:master
1m 24s
vendor : update vendored copy of google/minja Pull Request Labeler #14241: Pull request #15011 synchronize by l-austenfeld
10s
10s
vendor : update vendored copy of google/minja Pull Request Labeler #14240: Pull request #15011 opened by l-austenfeld
16s
16s
Implementation of GGML_NUMA_MIRROR for inferencing performance gain on numa systems Pull Request Labeler #14239: Pull request #14969 synchronize by dbsanfte
5m 58s
5m 58s
vulkan: optimizations for direct convolution EditorConfig Checker #28730: Pull request #14933 synchronize by jeffbolznv
21s jeffbolznv:conv_opt
jeffbolznv:conv_opt
21s
vulkan: optimizations for direct convolution Server #16998: Pull request #14933 synchronize by jeffbolznv
12m 50s jeffbolznv:conv_opt
jeffbolznv:conv_opt
12m 50s
vulkan: optimizations for direct convolution CI #25591: Pull request #14933 synchronize by jeffbolznv
1h 8m 33s jeffbolznv:conv_opt
jeffbolznv:conv_opt
1h 8m 33s
vulkan: optimizations for direct convolution Pull Request Labeler #14238: Pull request #14933 synchronize by jeffbolznv
10s
10s
model : add hunyuan dense (#14878) Python Type-Check #3674: Commit 0f5ccd6 pushed by CISC
1m 59s master
master
1m 59s
model : add hunyuan dense (#14878) EditorConfig Checker #28729: Commit 0f5ccd6 pushed by CISC
21s master
master
21s
model : add hunyuan dense (#14878) Python check requirements.txt #3899: Commit 0f5ccd6 pushed by CISC
3m 12s master
master
3m 12s