Skip to content

Actions: ggml-org/llama.cpp

Actions

All workflows

Actions

Loading...
Loading

Showing runs from all workflows
58,920 workflow run results
58,920 workflow run results

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

ci : cache ROCm installation in windows-latest-cmake-hip EditorConfig Checker #30699: Pull request #15887 synchronize by danbev
55m 0s danbev:ci-windows-lastest-cmake-hip
danbev:ci-windows-lastest-cmake-hip
55m 0s
ci : cache ROCm installation in windows-latest-cmake-hip CI #27301: Pull request #15887 synchronize by danbev
4h 28m 40s danbev:ci-windows-lastest-cmake-hip
danbev:ci-windows-lastest-cmake-hip
4h 28m 40s
ci : cache ROCm installation in windows-latest-cmake-hip Build on RISCV Linux Machine by Cloud-V #913: Pull request #15887 synchronize by danbev
5m 2s danbev:ci-windows-lastest-cmake-hip
danbev:ci-windows-lastest-cmake-hip
5m 2s
ci : cache ROCm installation in windows-latest-cmake-hip Pull Request Labeler #16011: Pull request #15887 synchronize by danbev
41m 0s
41m 0s
Add docker protocol support for llama-server model loading CI #27300: Pull request #15790 synchronize by ericcurtin
1h 28m 55s docker-pull-functionality
docker-pull-functionality
1h 28m 55s
Add docker protocol support for llama-server model loading Server #18730: Pull request #15790 synchronize by ericcurtin
1h 28m 48s docker-pull-functionality
docker-pull-functionality
1h 28m 48s
Add docker protocol support for llama-server model loading EditorConfig Checker #30698: Pull request #15790 synchronize by ericcurtin
5m 48s docker-pull-functionality
docker-pull-functionality
5m 48s
Add docker protocol support for llama-server model loading Build on RISCV Linux Machine by Cloud-V #912: Pull request #15790 synchronize by ericcurtin
8m 2s docker-pull-functionality
docker-pull-functionality
8m 2s
Add docker protocol support for llama-server model loading Pull Request Labeler #16010: Pull request #15790 synchronize by ericcurtin
40m 8s
40m 8s
vulkan: Fix OOB accesses in soft_max_back (#15861) Release #878: Commit 4f63cd7 pushed by 0cc4m
1h 32m 19s master
master
1h 32m 19s
vulkan: Fix OOB accesses in soft_max_back (#15861) CI #27299: Commit 4f63cd7 pushed by 0cc4m
4h 12m 56s master
master
4h 12m 56s
vulkan: Fix OOB accesses in soft_max_back (#15861) Server #18729: Commit 4f63cd7 pushed by 0cc4m
53m 18s master
master
53m 18s
vulkan: Fix OOB accesses in soft_max_back (#15861) EditorConfig Checker #30697: Commit 4f63cd7 pushed by 0cc4m
10m 52s master
master
10m 52s
HIP: use v_dot2_f32_f16 instruction for FA (#15884) EditorConfig Checker #30696: Commit 17bc5a8 pushed by JohannesGaessler
4m 7s master
master
4m 7s
HIP: use v_dot2_f32_f16 instruction for FA (#15884) Release #877: Commit 17bc5a8 pushed by JohannesGaessler
2h 0m 59s master
master
2h 0m 59s
HIP: use v_dot2_f32_f16 instruction for FA (#15884) CI #27298: Commit 17bc5a8 pushed by JohannesGaessler
1h 0m 4s master
master
1h 0m 4s
HIP: use v_dot2_f32_f16 instruction for FA (#15884) Server #18728: Commit 17bc5a8 pushed by JohannesGaessler
40m 47s master
master
40m 47s
metal : make the backend async CI #27297: Pull request #15832 synchronize by ggerganov
1h 55m 43s gg/metal-async
gg/metal-async
1h 55m 43s
metal : make the backend async Build on RISCV Linux Machine by Cloud-V #911: Pull request #15832 synchronize by ggerganov
5m 0s gg/metal-async
gg/metal-async
5m 0s
metal : make the backend async EditorConfig Checker #30695: Pull request #15832 synchronize by ggerganov
6m 15s gg/metal-async
gg/metal-async
6m 15s
metal : make the backend async Server #18727: Pull request #15832 synchronize by ggerganov
21m 37s gg/metal-async
gg/metal-async
21m 37s
metal : make the backend async Pull Request Labeler #16009: Pull request #15832 synchronize by ggerganov
10m 12s
10m 12s
Workaround for subgroup arithmetic failing on MoltenVK with AMD GPUs … EditorConfig Checker #30694: Commit ed54e32 pushed by 0cc4m
22s master
master
22s
Workaround for subgroup arithmetic failing on MoltenVK with AMD GPUs … Release #876: Commit ed54e32 pushed by 0cc4m
1h 41m 36s master
master
1h 41m 36s
Workaround for subgroup arithmetic failing on MoltenVK with AMD GPUs … CI #27296: Commit ed54e32 pushed by 0cc4m
1h 46m 28s master
master
1h 46m 28s