Skip to content

Actions: ggml-org/llama.cpp

Actions

All workflows

Actions

Loading...
Loading

Showing runs from all workflows
31,962 workflow run results
31,962 workflow run results

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

llama-bench: add -d depth arg Pull Request Labeler #10443: Pull request #13096 synchronize by thevishalagarwal
6m 58s
6m 58s
clip : fix pixtral on some GPU backends Server #13127: Pull request #13097 synchronize by ngxson
17m 49s ngxson:xsn/pixtral_fix_backend
ngxson:xsn/pixtral_fix_backend
17m 49s
clip : fix pixtral on some GPU backends CI #21758: Pull request #13097 synchronize by ngxson
18m 6s ngxson:xsn/pixtral_fix_backend
ngxson:xsn/pixtral_fix_backend
18m 6s
clip : fix pixtral on some GPU backends EditorConfig Checker #24402: Pull request #13097 synchronize by ngxson
15m 12s ngxson:xsn/pixtral_fix_backend
ngxson:xsn/pixtral_fix_backend
15m 12s
clip : fix pixtral on some GPU backends Pull Request Labeler #10442: Pull request #13097 synchronize by ngxson
8m 26s
8m 26s
CUDA: use switch statements in constexpr functions (#13095) Server #13126: Commit b10d8bf pushed by JohannesGaessler
47m 32s master
master
47m 32s
CUDA: use switch statements in constexpr functions (#13095) EditorConfig Checker #24401: Commit b10d8bf pushed by JohannesGaessler
27m 3s master
master
27m 3s
CUDA: use switch statements in constexpr functions (#13095) CI #21757: Commit b10d8bf pushed by JohannesGaessler
3h 28m 51s master
master
3h 28m 51s
sync : ggml EditorConfig Checker #24400: Pull request #13098 opened by ggerganov
32m 59s sync-ggml-25-04-24
sync-ggml-25-04-24
32m 59s
sync : ggml Server #13125: Pull request #13098 opened by ggerganov
44m 28s sync-ggml-25-04-24
sync-ggml-25-04-24
44m 28s
sync : ggml CI #21756: Pull request #13098 opened by ggerganov
44m 36s sync-ggml-25-04-24
sync-ggml-25-04-24
44m 36s
sync : ggml Pull Request Labeler #10441: Pull request #13098 opened by ggerganov
14m 25s
14m 25s
clip : fix pixtral on some GPU backends Server #13124: Pull request #13097 opened by ngxson
29m 8s ngxson:xsn/pixtral_fix_backend
ngxson:xsn/pixtral_fix_backend
29m 8s
clip : fix pixtral on some GPU backends CI #21755: Pull request #13097 opened by ngxson
31m 46s ngxson:xsn/pixtral_fix_backend
ngxson:xsn/pixtral_fix_backend
31m 46s
clip : fix pixtral on some GPU backends Pull Request Labeler #10440: Pull request #13097 opened by ngxson
14m 22s
14m 22s
clip : fix pixtral on some GPU backends EditorConfig Checker #24399: Pull request #13097 opened by ngxson
19m 42s ngxson:xsn/pixtral_fix_backend
ngxson:xsn/pixtral_fix_backend
19m 42s
[WIP]backend: Integrating QNN (Qualcomm AI Engine Direct) as a dedicated backend for Qualcomm NPUs Pull Request Labeler #10439: Pull request #12063 synchronize by chraac
21m 34s
21m 34s
kv-cache : separate recurrent vs non-recurrent impl CI #21753: Pull request #12799 synchronize by ggerganov
1h 47m 49s gg/llama-kv-cache-v6
gg/llama-kv-cache-v6
1h 47m 49s
kv-cache : separate recurrent vs non-recurrent impl Server #13122: Pull request #12799 synchronize by ggerganov
41m 49s gg/llama-kv-cache-v6
gg/llama-kv-cache-v6
41m 49s
kv-cache : separate recurrent vs non-recurrent impl EditorConfig Checker #24397: Pull request #12799 synchronize by ggerganov
8m 20s gg/llama-kv-cache-v6
gg/llama-kv-cache-v6
8m 20s
model : better llama_model::create_model() signature Python Type-Check #2428: Commit d31e31d pushed by ggerganov
10m 53s gg/llama-kv-cache-v6
gg/llama-kv-cache-v6
10m 53s
kv-cache : separate recurrent vs non-recurrent impl Pull Request Labeler #10438: Pull request #12799 synchronize by ggerganov
11m 58s
11m 58s
model : better llama_model::create_model() signature Python check requirements.txt #2937: Commit d31e31d pushed by ggerganov
11m 48s gg/llama-kv-cache-v6
gg/llama-kv-cache-v6
11m 48s
kv-cache : separate recurrent vs non-recurrent impl CI #21752: Pull request #12799 synchronize by ggerganov
5m 17s gg/llama-kv-cache-v6
gg/llama-kv-cache-v6
5m 17s
kv-cache : separate recurrent vs non-recurrent impl Server #13121: Pull request #12799 synchronize by ggerganov
5m 14s gg/llama-kv-cache-v6
gg/llama-kv-cache-v6
5m 14s
ProTip! You can narrow down the results and go further in time using created:<2025-04-24 or the other filters available.