Skip to content

Actions: ggml-org/llama.cpp

Actions

All workflows

Actions

Loading...
Loading

Showing runs from all workflows
47,425 workflow run results
47,425 workflow run results

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

Fix KleidiAI compilation errors with -DGGML_NATIVE=OFF (issue #14464) CI #25033: Pull request #14700 synchronize by baonudesifeizhai
1h 11m 30s baonudesifeizhai:fix-kleidiai-zero-size-array-issue-14464
baonudesifeizhai:fix-kleidiai-zero-size-array-issue-14464
1h 11m 30s
Fix KleidiAI compilation errors with -DGGML_NATIVE=OFF (issue #14464) EditorConfig Checker #28046: Pull request #14700 synchronize by baonudesifeizhai
19m 26s baonudesifeizhai:fix-kleidiai-zero-size-array-issue-14464
baonudesifeizhai:fix-kleidiai-zero-size-array-issue-14464
19m 26s
Fix KleidiAI compilation errors with -DGGML_NATIVE=OFF (issue #14464) Server #16427: Pull request #14700 synchronize by baonudesifeizhai
30m 11s baonudesifeizhai:fix-kleidiai-zero-size-array-issue-14464
baonudesifeizhai:fix-kleidiai-zero-size-array-issue-14464
30m 11s
Fix KleidiAI compilation errors with -DGGML_NATIVE=OFF (issue #14464) Pull Request Labeler #13661: Pull request #14700 synchronize by baonudesifeizhai
11s
11s
OpenCL: add conv2d kernel Pull Request Labeler #13660: Pull request #14403 synchronize by rmatif
1m 34s
1m 34s
finetune: SGD optimizer, more CLI args Server #16426: Pull request #13873 synchronize by graehl
11m 45s graehl:finelayer
graehl:finelayer
11m 45s
finetune: SGD optimizer, more CLI args CI #25032: Pull request #13873 synchronize by graehl
1h 6m 47s graehl:finelayer
graehl:finelayer
1h 6m 47s
finetune: SGD optimizer, more CLI args EditorConfig Checker #28045: Pull request #13873 synchronize by graehl
23s graehl:finelayer
graehl:finelayer
23s
finetune: SGD optimizer, more CLI args Pull Request Labeler #13659: Pull request #13873 synchronize by graehl
53s
53s
ggml: Add initial WebGPU backend (#14521) EditorConfig Checker #28044: Commit 21c0217 pushed by ggerganov
15m 57s master
master
15m 57s
ggml: Add initial WebGPU backend (#14521) Python Type-Check #3464: Commit 21c0217 pushed by ggerganov
13m 19s master
master
13m 19s
ggml: Add initial WebGPU backend (#14521) flake8 Lint #18834: Commit 21c0217 pushed by ggerganov
23m 59s master
master
23m 59s
ggml: Add initial WebGPU backend (#14521) CI #25031: Commit 21c0217 pushed by ggerganov
1h 26m 25s master
master
1h 26m 25s
ggml: Add initial WebGPU backend (#14521) Release #478: Commit 21c0217 pushed by ggerganov
56m 26s master
master
56m 26s
ggml: Add initial WebGPU backend (#14521) Server #16425: Commit 21c0217 pushed by ggerganov
54m 42s master
master
54m 42s
Fix parameter order issue for hybrid memory initialization EditorConfig Checker #28043: Pull request #14725 opened by dinerburger
13m 46s dinerburger:fix-hybrid
dinerburger:fix-hybrid
13m 46s
Fix parameter order issue for hybrid memory initialization CI #25030: Pull request #14725 opened by dinerburger
1h 24m 45s dinerburger:fix-hybrid
dinerburger:fix-hybrid
1h 24m 45s
Fix parameter order issue for hybrid memory initialization Server #16424: Pull request #14725 opened by dinerburger
53m 8s dinerburger:fix-hybrid
dinerburger:fix-hybrid
53m 8s
Fix parameter order issue for hybrid memory initialization Pull Request Labeler #13658: Pull request #14725 opened by dinerburger
13m 50s
13m 50s
model : support output bias for qwen2 (#14711) Server #16423: Commit b0f0ecc pushed by ggerganov
46m 27s master
master
46m 27s
model : support output bias for qwen2 (#14711) EditorConfig Checker #28042: Commit b0f0ecc pushed by ggerganov
49s master
master
49s
model : support output bias for qwen2 (#14711) CI #25029: Commit b0f0ecc pushed by ggerganov
1h 19m 49s master
master
1h 19m 49s
model : support output bias for qwen2 (#14711) Release #477: Commit b0f0ecc pushed by ggerganov
1h 7m 54s master
master
1h 7m 54s
llama : reuse compute graphs Pull Request Labeler #13657: Pull request #14482 synchronize by ggerganov
12s
12s
ggml: Add initial WebGPU backend Server #16422: Pull request #14521 synchronize by reeselevine
12m 13s reeselevine:webgpu
reeselevine:webgpu
12m 13s