Skip to content

Actions: ggml-org/llama.cpp

Actions

All workflows

Actions

Loading...
Loading

Showing runs from all workflows
73,459 workflow run results
73,459 workflow run results

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

ggml: CUDA: add head size 72 for flash-attn (#16962) Server #21323: Commit 622cd01 pushed by ngxson
3h 36m 7s master
master
3h 36m 7s
Build Actions Cache Build Actions Cache #671: Scheduled
1h 7m 40s master
master
1h 7m 40s
sycl: flash-attention implementation EditorConfig Checker #33601: Pull request #16969 opened by ye-NX
1h 49m 46s ye-NX:saf-ye/flash-attn
ye-NX:saf-ye/flash-attn
1h 49m 46s
sycl: flash-attention implementation Build on RISCV Linux Machine by Cloud-V #3363: Pull request #16969 opened by ye-NX
6m 55s ye-NX:saf-ye/flash-attn
ye-NX:saf-ye/flash-attn
6m 55s
sycl: flash-attention implementation Server #21322: Pull request #16969 opened by ye-NX
3h 42m 22s ye-NX:saf-ye/flash-attn
ye-NX:saf-ye/flash-attn
3h 42m 22s
sycl: flash-attention implementation CI #29745: Pull request #16969 opened by ye-NX
3h 22m 58s ye-NX:saf-ye/flash-attn
ye-NX:saf-ye/flash-attn
3h 22m 58s
sycl: flash-attention implementation Pull Request Labeler #18797: Pull request #16969 opened by ye-NX
2h 29m 50s
2h 29m 50s
cann: update cross_entropy_loss op support Build on RISCV Linux Machine by Cloud-V #3362: Pull request #16886 synchronize by TecJesh
6m 52s TecJesh:cross_entropy_loss
TecJesh:cross_entropy_loss
6m 52s
cann: update cross_entropy_loss op support EditorConfig Checker #33600: Pull request #16886 synchronize by TecJesh
39m 44s TecJesh:cross_entropy_loss
TecJesh:cross_entropy_loss
39m 44s
cann: update cross_entropy_loss op support Server #21321: Pull request #16886 synchronize by TecJesh
1h 52m 17s TecJesh:cross_entropy_loss
TecJesh:cross_entropy_loss
1h 52m 17s
cann: update cross_entropy_loss op support CI #29744: Pull request #16886 synchronize by TecJesh
6m 51s TecJesh:cross_entropy_loss
TecJesh:cross_entropy_loss
6m 51s
cann: update cross_entropy_loss op support Pull Request Labeler #18796: Pull request #16886 synchronize by TecJesh
2h 55m 29s
2h 55m 29s
Implement SparseK Attention mechanism — new GGML operator with CPU backend (GPU planned next) EditorConfig Checker #33599: Pull request #16817 synchronize by GittyBurstein
1h 17m 45s yael-works:feature/sparsek-attn-sycl
yael-works:feature/sparsek-attn-sycl
1h 17m 45s
Implement SparseK Attention mechanism — new GGML operator with CPU backend (GPU planned next) CI #29743: Pull request #16817 synchronize by GittyBurstein
3h 8m 45s yael-works:feature/sparsek-attn-sycl
yael-works:feature/sparsek-attn-sycl
3h 8m 45s
Implement SparseK Attention mechanism — new GGML operator with CPU backend (GPU planned next) Build on RISCV Linux Machine by Cloud-V #3361: Pull request #16817 synchronize by GittyBurstein
3m 7s yael-works:feature/sparsek-attn-sycl
yael-works:feature/sparsek-attn-sycl
3m 7s
Implement SparseK Attention mechanism — new GGML operator with CPU backend (GPU planned next) Server #21320: Pull request #16817 synchronize by GittyBurstein
4h 12m 32s yael-works:feature/sparsek-attn-sycl
yael-works:feature/sparsek-attn-sycl
4h 12m 32s
Implement SparseK Attention mechanism — new GGML operator with CPU backend (GPU planned next) Pull Request Labeler #18795: Pull request #16817 synchronize by GittyBurstein
3h 0m 16s
3h 0m 16s
bench : cache the llama_context state at computed depth CI #29742: Pull request #16944 synchronize by ggerganov
1h 41m 1s gg/context-skip-compute
gg/context-skip-compute
1h 41m 1s
bench : cache the llama_context state at computed depth Server #21319: Pull request #16944 synchronize by ggerganov
1h 40m 53s gg/context-skip-compute
gg/context-skip-compute
1h 40m 53s
bench : cache the llama_context state at computed depth EditorConfig Checker #33598: Pull request #16944 synchronize by ggerganov
1h 40m 41s gg/context-skip-compute
gg/context-skip-compute
1h 40m 41s
bench : cache the llama_context state at computed depth Build on RISCV Linux Machine by Cloud-V #3360: Pull request #16944 synchronize by ggerganov
8m 20s gg/context-skip-compute
gg/context-skip-compute
8m 20s
bench : cache the llama_context state at computed depth Pull Request Labeler #18794: Pull request #16944 synchronize by ggerganov
3h 9m 36s
3h 9m 36s
Build Actions Cache Build Actions Cache #670: Scheduled
1h 6m 45s master
master
1h 6m 45s
s390x: disable vxe for cross-compilation by default EditorConfig Checker #33597: Pull request #16966 opened by AlekseiNikiforovIBM
2h 30m 1s AlekseiNikiforovIBM:s390x_vxe_cross
AlekseiNikiforovIBM:s390x_vxe_cross
2h 30m 1s
s390x: disable vxe for cross-compilation by default CI #29741: Pull request #16966 opened by AlekseiNikiforovIBM
4h 20m 38s AlekseiNikiforovIBM:s390x_vxe_cross
AlekseiNikiforovIBM:s390x_vxe_cross
4h 20m 38s