Skip to content

Actions: ggml-org/llama.cpp

Actions

All workflows

Actions

Loading...
Loading

Showing runs from all workflows
47,855 workflow run results
47,855 workflow run results

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

metal : fuse add, mul CI #25103: Pull request #14596 synchronize by ggerganov
7m 2s gg/metal-fuse-add
gg/metal-fuse-add
7m 2s
metal : fuse add, mul Server #16495: Pull request #14596 synchronize by ggerganov
7m 5s gg/metal-fuse-add
gg/metal-fuse-add
7m 5s
metal : fuse add, mul Pull Request Labeler #13722: Pull request #14596 synchronize by ggerganov
1m 58s
1m 58s
metal : fuse add, mul + add tests Python check requirements.txt #3744: Commit 04d0349 pushed by ggerganov
10m 40s gg/metal-fuse-add
gg/metal-fuse-add
10m 40s
metal : fuse add, mul + add tests Python Type-Check #3483: Commit 04d0349 pushed by ggerganov
11m 3s gg/metal-fuse-add
gg/metal-fuse-add
11m 3s
cuda : Fix Gemma3n not executed as CUDA_GRAPH on NVGPUs (#14741) Release #493: Commit 021cc28 pushed by slaren
44m 21s master
master
44m 21s
cuda : Fix Gemma3n not executed as CUDA_GRAPH on NVGPUs (#14741) EditorConfig Checker #28124: Commit 021cc28 pushed by slaren
1m 11s master
master
1m 11s
cuda : Fix Gemma3n not executed as CUDA_GRAPH on NVGPUs (#14741) Server #16494: Commit 021cc28 pushed by slaren
16m 51s master
master
16m 51s
cuda : Fix Gemma3n not executed as CUDA_GRAPH on NVGPUs (#14741) CI #25102: Commit 021cc28 pushed by slaren
1h 35m 1s master
master
1h 35m 1s
graph : avoid huge warm-up graphs for MoE models (#14753) EditorConfig Checker #28123: Commit d498af3 pushed by ggerganov
20s master
master
20s
graph : avoid huge warm-up graphs for MoE models (#14753) Release #492: Commit d498af3 pushed by ggerganov
46m 2s master
master
46m 2s
graph : avoid huge warm-up graphs for MoE models (#14753) Server #16493: Commit d498af3 pushed by ggerganov
11m 44s master
master
11m 44s
graph : avoid huge warm-up graphs for MoE models (#14753) CI #25101: Commit d498af3 pushed by ggerganov
1h 18m 38s master
master
1h 18m 38s
graph : avoid huge warm-up graphs for MoE models Pull Request Labeler #13721: Pull request #14753 synchronize by ggerganov
11s
11s
graph : avoid huge warm-up graphs for MoE models EditorConfig Checker #28122: Pull request #14753 synchronize by ggerganov
24s gg/context-reduce-min-nodes
gg/context-reduce-min-nodes
24s
graph : avoid huge warm-up graphs for MoE models CI #25100: Pull request #14753 synchronize by ggerganov
1h 2m 55s gg/context-reduce-min-nodes
gg/context-reduce-min-nodes
1h 2m 55s
graph : avoid huge warm-up graphs for MoE models Server #16492: Pull request #14753 synchronize by ggerganov
12m 35s gg/context-reduce-min-nodes
gg/context-reduce-min-nodes
12m 35s
tests : add non-cont K,V FA tests Pull Request Labeler #13720: Pull request #14756 opened by ggerganov
11s
11s
tests : add non-cont K,V FA tests EditorConfig Checker #28121: Pull request #14756 opened by ggerganov
17s gg/tests-fa-non-cont
gg/tests-fa-non-cont
17s
tests : add non-cont K,V FA tests Server #16491: Pull request #14756 opened by ggerganov
11m 48s gg/tests-fa-non-cont
gg/tests-fa-non-cont
11m 48s
tests : add non-cont K,V FA tests CI #25099: Pull request #14756 opened by ggerganov
55m 17s gg/tests-fa-non-cont
gg/tests-fa-non-cont
55m 17s
Fix Gemma3n not executed as CUDA_GRAPH on NVGPUs Server #16490: Pull request #14741 synchronize by ORippler
23m 39s ORippler:hotfix_perf_issues_of_gemma3n
ORippler:hotfix_perf_issues_of_gemma3n
23m 39s
Fix Gemma3n not executed as CUDA_GRAPH on NVGPUs CI #25098: Pull request #14741 synchronize by ORippler
1h 1m 36s ORippler:hotfix_perf_issues_of_gemma3n
ORippler:hotfix_perf_issues_of_gemma3n
1h 1m 36s
Fix Gemma3n not executed as CUDA_GRAPH on NVGPUs EditorConfig Checker #28120: Pull request #14741 synchronize by ORippler
5m 17s ORippler:hotfix_perf_issues_of_gemma3n
ORippler:hotfix_perf_issues_of_gemma3n
5m 17s
Fix Gemma3n not executed as CUDA_GRAPH on NVGPUs Pull Request Labeler #13719: Pull request #14741 synchronize by ORippler
12s
12s