Skip to content

Actions: ggml-org/llama.cpp

Actions

All workflows

Actions

Loading...
Loading

Showing runs from all workflows
44,755 workflow run results
44,755 workflow run results

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

test-backend-ops: add support for specifying output format Pull Request Labeler #13107: Pull request #14368 synchronize by yeahdongcn
11s
11s
Close inactive issues Close inactive issues #475: Scheduled
49s master
master
49s
finetune: SGD optimizer, more CLI args Pull Request Labeler #13106: Pull request #13873 synchronize by graehl
10s
10s
finetune: SGD optimizer, more CLI args Pull Request Labeler #13105: Pull request #13873 synchronize by graehl
3m 3s
3m 3s
llama : support Jamba hybrid Transformer-Mamba models CI #24463: Pull request #7531 synchronize by compilade
1h 25m 25s compilade/refactor-kv-cache
compilade/refactor-kv-cache
1h 25m 25s
llama : support Jamba hybrid Transformer-Mamba models EditorConfig Checker #27447: Pull request #7531 synchronize by compilade
5m 42s compilade/refactor-kv-cache
compilade/refactor-kv-cache
5m 42s
llama : support Jamba hybrid Transformer-Mamba models Server #15859: Pull request #7531 synchronize by compilade
18m 10s compilade/refactor-kv-cache
compilade/refactor-kv-cache
18m 10s
llama : support Jamba hybrid Transformer-Mamba models flake8 Lint #18567: Pull request #7531 synchronize by compilade
12m 16s compilade/refactor-kv-cache
compilade/refactor-kv-cache
12m 16s
llama : support Jamba hybrid Transformer-Mamba models Python Type-Check #3163: Pull request #7531 synchronize by compilade
8m 59s compilade/refactor-kv-cache
compilade/refactor-kv-cache
8m 59s
llama : support Jamba hybrid Transformer-Mamba models Python check requirements.txt #3471: Pull request #7531 synchronize by compilade
8m 12s compilade/refactor-kv-cache
compilade/refactor-kv-cache
8m 12s
model : add Jamba to Mamba-specific hparams printing Python check requirements.txt #3470: Commit 07c252f pushed by compilade
3m 11s compilade/refactor-kv-cache
compilade/refactor-kv-cache
3m 11s
llama : support Jamba hybrid Transformer-Mamba models Pull Request Labeler #13104: Pull request #7531 synchronize by compilade
5m 54s
5m 54s
model : add Jamba to Mamba-specific hparams printing Python Type-Check #3162: Commit 07c252f pushed by compilade
1m 23s compilade/refactor-kv-cache
compilade/refactor-kv-cache
1m 23s
webui : add a preset feature to the settings EditorConfig Checker #27446: Pull request #14523 opened by gabriellarson
19s gabriellarson:master
gabriellarson:master
19s
webui : add a preset feature to the settings Server #15858: Pull request #14523 opened by gabriellarson
11m 4s gabriellarson:master
gabriellarson:master
11m 4s
webui : add a preset feature to the settings Pull Request Labeler #13103: Pull request #14523 opened by gabriellarson
3m 6s
3m 6s
ggml : implement GEGLU_ERF and GEGLU_QUICK ops (#14445) Release #399: Commit 28657a8 pushed by CISC
1h 7m 46s master
master
1h 7m 46s
ggml : implement GEGLU_ERF and GEGLU_QUICK ops (#14445) CI #24462: Commit 28657a8 pushed by CISC
1h 7m 42s master
master
1h 7m 42s
ggml : implement GEGLU_ERF and GEGLU_QUICK ops (#14445) Server #15857: Commit 28657a8 pushed by CISC
29m 44s master
master
29m 44s
ggml : implement GEGLU_ERF and GEGLU_QUICK ops (#14445) EditorConfig Checker #27445: Commit 28657a8 pushed by CISC
17s master
master
17s
train: add simple loading already tokenized data from parquet dataset CI #24461: Pull request #14522 synchronize by lexasub
1h 8m 11s lexasub:parquet2
lexasub:parquet2
1h 8m 11s
train: add simple loading already tokenized data from parquet dataset EditorConfig Checker #27444: Pull request #14522 synchronize by lexasub
17s lexasub:parquet2
lexasub:parquet2
17s
train: add simple loading already tokenized data from parquet dataset Server #15856: Pull request #14522 synchronize by lexasub
11m 35s lexasub:parquet2
lexasub:parquet2
11m 35s
train: add simple loading already tokenized data from parquet dataset Pull Request Labeler #13102: Pull request #14522 synchronize by lexasub
15s
15s
train: add simple loading already tokenized data from parquet dataset EditorConfig Checker #27443: Pull request #14522 synchronize by lexasub
24s lexasub:parquet2
lexasub:parquet2
24s
ProTip! You can narrow down the results and go further in time using created:<2025-07-03 or the other filters available.