Skip to content

Actions: ggml-org/llama.cpp

Actions

All workflows

Actions

Loading...
Loading

Showing runs from all workflows
37,942 workflow run results
37,942 workflow run results

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

kv-cache : avoid modifying recurrent cells when setting inputs Server #14436: Pull request #13834 opened by compilade
24m 13s compilade/readonly-recurrent-inputs
compilade/readonly-recurrent-inputs
24m 13s
kv-cache : avoid modifying recurrent cells when setting inputs CI #23039: Pull request #13834 opened by compilade
1h 26m 12s compilade/readonly-recurrent-inputs
compilade/readonly-recurrent-inputs
1h 26m 12s
kv-cache : avoid modifying recurrent cells when setting inputs Pull Request Labeler #11703: Pull request #13834 opened by compilade
3m 46s
3m 46s
llama : use n_swa + n_ubatch cells for SWA cache CI #23038: Pull request #13833 opened by ggerganov
2h 3m 55s gg/swa-optimize
gg/swa-optimize
2h 3m 55s
llama : use n_swa + n_ubatch cells for SWA cache Server #14435: Pull request #13833 opened by ggerganov
56m 59s gg/swa-optimize
gg/swa-optimize
56m 59s
llama : use n_swa + n_ubatch cells for SWA cache Pull Request Labeler #11702: Pull request #13833 opened by ggerganov
44m 52s
44m 52s
vulkan: use timestamp queries for GGML_VULKAN_PERF (#13817) CI #23037: Commit bef8176 pushed by 0cc4m
2h 29m 46s master
master
2h 29m 46s
vulkan: use timestamp queries for GGML_VULKAN_PERF (#13817) EditorConfig Checker #25888: Commit bef8176 pushed by 0cc4m
55m 6s master
master
55m 6s
vulkan: use timestamp queries for GGML_VULKAN_PERF (#13817) Server #14434: Commit bef8176 pushed by 0cc4m
1h 6m 2s master
master
1h 6m 2s
vulkan: use timestamp queries for GGML_VULKAN_PERF (#13817) Release #165: Commit bef8176 pushed by 0cc4m
2h 11m 14s master
master
2h 11m 14s
cmake : add llama-cparams.cpp to build (#13832) EditorConfig Checker #25887: Commit 34b7c04 pushed by ggerganov
1h 1m 39s master
master
1h 1m 39s
cmake : add llama-cparams.cpp to build (#13832) CI #23036: Commit 34b7c04 pushed by ggerganov
2h 18m 14s master
master
2h 18m 14s
cmake : add llama-cparams.cpp to build (#13832) Server #14433: Commit 34b7c04 pushed by ggerganov
1h 16m 46s master
master
1h 16m 46s
cmake : add llama-cparams.cpp to build (#13832) Release #164: Commit 34b7c04 pushed by ggerganov
2h 16m 4s master
master
2h 16m 4s
cmake : add llama-cparams.cpp to build Server #14432: Pull request #13832 opened by ggerganov
54m 36s gg/cparams-fix-build
gg/cparams-fix-build
54m 36s
cmake : add llama-cparams.cpp to build EditorConfig Checker #25886: Pull request #13832 opened by ggerganov
46m 27s gg/cparams-fix-build
gg/cparams-fix-build
46m 27s
cmake : add llama-cparams.cpp to build CI #23035: Pull request #13832 opened by ggerganov
2h 5m 41s gg/cparams-fix-build
gg/cparams-fix-build
2h 5m 41s
cmake : add llama-cparams.cpp to build Pull Request Labeler #11701: Pull request #13832 opened by ggerganov
1h 1m 45s
1h 1m 45s
[WIP]backend: Integrating QNN (Qualcomm AI Engine Direct) as a dedicated backend for Qualcomm NPUs Pull Request Labeler #11700: Pull request #12063 synchronize by chraac
23m 6s
23m 6s
convert: handle when model's tokenization method relies on Mecab Pull Request Labeler #11699: Pull request #13830 opened by huydt84
53m 19s
53m 19s
SYCL: add gelu_erf kernel (#13749) Server #14430: Commit f3101a8 pushed by qnixsynapse
1h 3m 58s master
master
1h 3m 58s
SYCL: add gelu_erf kernel (#13749) EditorConfig Checker #25883: Commit f3101a8 pushed by qnixsynapse
52m 22s master
master
52m 22s
SYCL: add gelu_erf kernel (#13749) CI #23033: Commit f3101a8 pushed by qnixsynapse
2h 32m 33s master
master
2h 32m 33s
SYCL: add gelu_erf kernel (#13749) Release #163: Commit f3101a8 pushed by qnixsynapse
2h 40m 8s master
master
2h 40m 8s
ggml-vulkan: adds support for op CONV_TRANSPOSE_1D Server #14429: Pull request #13813 synchronize by etasnadi
13m 28s etasnadi:ggml/vk_conv_transpose_1d
etasnadi:ggml/vk_conv_transpose_1d
13m 28s