Skip to content

Actions: ggml-org/llama.cpp

Actions

All workflows

Actions

Loading...
Loading

Showing runs from all workflows
44,263 workflow run results
44,263 workflow run results

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

llama : add high-throughput mode Pull Request Labeler #13079: Pull request #14363 synchronize by ggerganov
1h 12m 28s
1h 12m 28s
convert : correct gemma 3n conversion (#14450) Python Type-Check #3159: Commit 0c2ee38 pushed by ngxson
1h 15m 40s master
master
1h 15m 40s
convert : correct gemma 3n conversion (#14450) EditorConfig Checker #27416: Commit 0c2ee38 pushed by ngxson
1h 6m 2s master
master
1h 6m 2s
convert : correct gemma 3n conversion (#14450) flake8 Lint #18564: Commit 0c2ee38 pushed by ngxson
1h 22m 27s master
master
1h 22m 27s
llama : reuse compute graphs Server #15829: Pull request #14482 synchronize by ggerganov
1h 11m 11s gg/llama-reuse-graphs
gg/llama-reuse-graphs
1h 11m 11s
llama : reuse compute graphs EditorConfig Checker #27415: Pull request #14482 synchronize by ggerganov
1h 4m 12s gg/llama-reuse-graphs
gg/llama-reuse-graphs
1h 4m 12s
llama : reuse compute graphs CI #24434: Pull request #14482 synchronize by ggerganov
3h 18m 43s gg/llama-reuse-graphs
gg/llama-reuse-graphs
3h 18m 43s
llama : reuse compute graphs Pull Request Labeler #13078: Pull request #14482 synchronize by ggerganov
1h 0m 46s
1h 0m 46s
llama : reuse compute graphs Python check requirements.txt #3468: Commit d9e1781 pushed by ggerganov
1h 32m 20s gg/llama-reuse-graphs
gg/llama-reuse-graphs
1h 32m 20s
llama : reuse compute graphs Python Type-Check #3158: Commit d9e1781 pushed by ggerganov
1h 3m 42s gg/llama-reuse-graphs
gg/llama-reuse-graphs
1h 3m 42s
llama : add high-throughput mode Server #15828: Pull request #14363 synchronize by ggerganov
13m 53s gg/llama-high-throughput
gg/llama-high-throughput
13m 53s
llama : add high-throughput mode CI #24433: Pull request #14363 synchronize by ggerganov
13m 54s gg/llama-high-throughput
gg/llama-high-throughput
13m 54s
llama : add high-throughput mode EditorConfig Checker #27414: Pull request #14363 synchronize by ggerganov
13m 52s gg/llama-high-throughput
gg/llama-high-throughput
13m 52s
llama : add high-throughput mode Pull Request Labeler #13077: Pull request #14363 synchronize by ggerganov
1h 1m 55s
1h 1m 55s
llama : add "virtual sequences" Python Type-Check #3157: Commit eb5856c pushed by ggerganov
1h 14m 39s gg/llama-high-throughput
gg/llama-high-throughput
1h 14m 39s
llama : add "virtual sequences" Python check requirements.txt #3467: Commit eb5856c pushed by ggerganov
52m 3s gg/llama-high-throughput
gg/llama-high-throughput
52m 3s
kv-cache : use ggml_set_rows (#14285) EditorConfig Checker #27413: Commit a70c8a0 pushed by ggerganov
37m 22s master
master
37m 22s
kv-cache : use ggml_set_rows (#14285) Server #15827: Commit a70c8a0 pushed by ggerganov
1h 26m 17s master
master
1h 26m 17s
kv-cache : use ggml_set_rows (#14285) Release #394: Commit a70c8a0 pushed by ggerganov
3h 24m 17s master
master
3h 24m 17s
kv-cache : use ggml_set_rows (#14285) CI #24432: Commit a70c8a0 pushed by ggerganov
3h 36m 20s master
master
3h 36m 20s
test-backend-ops: add support for specifying output format EditorConfig Checker #27412: Pull request #14368 synchronize by yeahdongcn
28m 49s makllama:xd/test-backend-ops_sql
makllama:xd/test-backend-ops_sql
28m 49s
test-backend-ops: add support for specifying output format Pull Request Labeler #13076: Pull request #14368 synchronize by yeahdongcn
29m 56s
29m 56s
test-backend-ops: add support for specifying output format Server #15826: Pull request #14368 synchronize by yeahdongcn
34m 35s makllama:xd/test-backend-ops_sql
makllama:xd/test-backend-ops_sql
34m 35s
test-backend-ops: add support for specifying output format CI #24431: Pull request #14368 synchronize by yeahdongcn
2h 27m 8s makllama:xd/test-backend-ops_sql
makllama:xd/test-backend-ops_sql
2h 27m 8s
ggml : fix FA mask dim 2 and 3 (#14505) EditorConfig Checker #27411: Commit 9067487 pushed by ggerganov
40m 51s master
master
40m 51s
ProTip! You can narrow down the results and go further in time using created:<2025-07-03 or the other filters available.