Skip to content

Actions: ggml-org/llama.cpp

Actions

All workflows

Actions

Loading...
Loading

Showing runs from all workflows
73,575 workflow run results
73,575 workflow run results

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

server : do context shift only while generating (#17000) EditorConfig Checker #33703: Commit 66d8ecc pushed by ggerganov
1h 46m 12s master
master
1h 46m 12s
graph : reuse SSM graphs Build on RISCV Linux Machine by Cloud-V #3453: Pull request #16490 synchronize by ggerganov
18m 27s gg/graph-mamba-reuse
gg/graph-mamba-reuse
18m 27s
graph : reuse SSM graphs Server #21411: Pull request #16490 synchronize by ggerganov
7h 12m 2s gg/graph-mamba-reuse
gg/graph-mamba-reuse
7h 12m 2s
graph : reuse SSM graphs CI #29830: Pull request #16490 synchronize by ggerganov
7h 15m 42s gg/graph-mamba-reuse
gg/graph-mamba-reuse
7h 15m 42s
graph : reuse SSM graphs EditorConfig Checker #33702: Pull request #16490 synchronize by ggerganov
2h 16m 45s gg/graph-mamba-reuse
gg/graph-mamba-reuse
2h 16m 45s
Revert "memory : move the recurrent state into the memory context" Python Type-Check #4820: Commit 6bc704f pushed by ggerganov
1h 16m 24s gg/graph-mamba-reuse
gg/graph-mamba-reuse
1h 16m 24s
graph : reuse SSM graphs Pull Request Labeler #18891: Pull request #16490 synchronize by ggerganov
1h 38m 22s
1h 38m 22s
Revert "memory : move the recurrent state into the memory context" Check Pre-Tokenizer Hashes #718: Commit 6bc704f pushed by ggerganov
1h 14m 1s gg/graph-mamba-reuse
gg/graph-mamba-reuse
1h 14m 1s
Revert "memory : move the recurrent state into the memory context" Python check requirements.txt #4690: Commit 6bc704f pushed by ggerganov
1h 21m 58s gg/graph-mamba-reuse
gg/graph-mamba-reuse
1h 21m 58s
metal : initial Metal4 tensor API support CI #29829: Pull request #16634 synchronize by ggerganov
4h 20m 42s gg/metal-mul-mm-rework
gg/metal-mul-mm-rework
4h 20m 42s
metal : initial Metal4 tensor API support Build on RISCV Linux Machine by Cloud-V #3452: Pull request #16634 synchronize by ggerganov
6m 37s gg/metal-mul-mm-rework
gg/metal-mul-mm-rework
6m 37s
metal : initial Metal4 tensor API support EditorConfig Checker #33701: Pull request #16634 synchronize by ggerganov
1h 8m 35s gg/metal-mul-mm-rework
gg/metal-mul-mm-rework
1h 8m 35s
metal : initial Metal4 tensor API support Server #21410: Pull request #16634 synchronize by ggerganov
7h 7m 7s gg/metal-mul-mm-rework
gg/metal-mul-mm-rework
7h 7m 7s
metal : bf16 workaround (tmp) Update Operations Documentation #146: Commit 738b916 pushed by ggerganov
1h 25m 56s gg/metal-mul-mm-rework
gg/metal-mul-mm-rework
1h 25m 56s
metal : bf16 workaround (tmp) Python Type-Check #4819: Commit 738b916 pushed by ggerganov
50m 32s gg/metal-mul-mm-rework
gg/metal-mul-mm-rework
50m 32s
metal : initial Metal4 tensor API support Pull Request Labeler #18890: Pull request #16634 synchronize by ggerganov
53m 42s
53m 42s
metal : bf16 workaround (tmp) Python check requirements.txt #4689: Commit 738b916 pushed by ggerganov
58m 0s gg/metal-mul-mm-rework
gg/metal-mul-mm-rework
58m 0s
metal : bf16 workaround (tmp) Check Pre-Tokenizer Hashes #717: Commit 738b916 pushed by ggerganov
2h 9m 49s gg/metal-mul-mm-rework
gg/metal-mul-mm-rework
2h 9m 49s
sycl: flash-attention implementation Build on RISCV Linux Machine by Cloud-V #3451: Pull request #16969 synchronize by safranowith
6m 40s ye-NX:saf-ye/flash-attn
ye-NX:saf-ye/flash-attn
6m 40s
sycl: flash-attention implementation EditorConfig Checker #33700: Pull request #16969 synchronize by safranowith
26m 26s ye-NX:saf-ye/flash-attn
ye-NX:saf-ye/flash-attn
26m 26s
sycl: flash-attention implementation Server #21409: Pull request #16969 synchronize by safranowith
7h 21m 53s ye-NX:saf-ye/flash-attn
ye-NX:saf-ye/flash-attn
7h 21m 53s
sycl: flash-attention implementation CI #29828: Pull request #16969 synchronize by safranowith
5h 11m 56s ye-NX:saf-ye/flash-attn
ye-NX:saf-ye/flash-attn
5h 11m 56s
sycl: flash-attention implementation Pull Request Labeler #18889: Pull request #16969 synchronize by safranowith
22m 49s
22m 49s
Build Actions Cache Build Actions Cache #699: Scheduled
40m 38s master
master
40m 38s
improve CUDA cpy memory bandwidth when copying transposed tensor CI #29827: Pull request #16841 synchronize by bssrdf
4h 51m 39s bssrdf:cuda-transpose-cpy
bssrdf:cuda-transpose-cpy
4h 51m 39s