Skip to content

Actions: ggml-org/llama.cpp

Actions

All workflows

Actions

Loading...
Loading

Showing runs from all workflows
38,223 workflow run results
38,223 workflow run results

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

SYCL: Add mrope kernel (#13755) Release #186: Commit b49a8ff pushed by qnixsynapse
2h 37m 0s master
master
2h 37m 0s
kv-cache : split implementation in separate sources CI #23200: Pull request #13920 opened by ggerganov
29m 12s gg/kv-cache-split
gg/kv-cache-split
29m 12s
kv-cache : split implementation in separate sources Server #14594: Pull request #13920 opened by ggerganov
29m 7s gg/kv-cache-split
gg/kv-cache-split
29m 7s
kv-cache : split implementation in separate sources Pull Request Labeler #11876: Pull request #13920 opened by ggerganov
24m 31s
24m 31s
OpenCL: Add concat, tsembd, upscale, tanh, pad and repeat Server #14593: Pull request #13840 synchronize by rmatif
10m 49s rmatif:new-opencl-kernels-2
rmatif:new-opencl-kernels-2
10m 49s
OpenCL: Add concat, tsembd, upscale, tanh, pad and repeat EditorConfig Checker #26076: Pull request #13840 synchronize by rmatif
21s rmatif:new-opencl-kernels-2
rmatif:new-opencl-kernels-2
21s
OpenCL: Add concat, tsembd, upscale, tanh, pad and repeat CI #23199: Pull request #13840 synchronize by rmatif
1h 16m 2s rmatif:new-opencl-kernels-2
rmatif:new-opencl-kernels-2
1h 16m 2s
OpenCL: Add concat, tsembd, upscale, tanh, pad and repeat Pull Request Labeler #11875: Pull request #13840 synchronize by rmatif
56m 15s
56m 15s
llama : use n_swa + n_ubatch cells for SWA cache Server #14592: Pull request #13833 synchronize by ggerganov
30m 27s gg/swa-optimize
gg/swa-optimize
30m 27s
llama : use n_swa + n_ubatch cells for SWA cache CI #23198: Pull request #13833 synchronize by ggerganov
2h 20m 24s gg/swa-optimize
gg/swa-optimize
2h 20m 24s
llama : use n_swa + n_ubatch cells for SWA cache Pull Request Labeler #11874: Pull request #13833 synchronize by ggerganov
8m 15s
8m 15s
llama : use n_swa + n_ubatch cells for SWA cache Python check requirements.txt #3235: Commit ef5bb61 pushed by ggerganov
13m 33s gg/swa-optimize
gg/swa-optimize
13m 33s
llama : use n_swa + n_ubatch cells for SWA cache Python Type-Check #2885: Commit ef5bb61 pushed by ggerganov
4m 25s gg/swa-optimize
gg/swa-optimize
4m 25s
CUDA: add a prop in ggml_cuda_device_infor for distinguish iGPU or dGPU in cuda (#13856) EditorConfig Checker #26075: Pull request #13895 synchronize by Yangxiaoz
37m 0s Yangxiaoz:IntegrateCUDA
Yangxiaoz:IntegrateCUDA
37m 0s
CUDA: add a prop in ggml_cuda_device_infor for distinguish iGPU or dGPU in cuda (#13856) Server #14591: Pull request #13895 synchronize by Yangxiaoz
42m 21s Yangxiaoz:IntegrateCUDA
Yangxiaoz:IntegrateCUDA
42m 21s
CUDA: add a prop in ggml_cuda_device_infor for distinguish iGPU or dGPU in cuda (#13856) CI #23197: Pull request #13895 synchronize by Yangxiaoz
2h 51m 58s Yangxiaoz:IntegrateCUDA
Yangxiaoz:IntegrateCUDA
2h 51m 58s
CUDA: add a prop in ggml_cuda_device_infor for distinguish iGPU or dGPU in cuda (#13856) Pull Request Labeler #11873: Pull request #13895 synchronize by Yangxiaoz
45m 14s
45m 14s
cuda : prevent using split buffers with 3d/4d matrices EditorConfig Checker #26074: Pull request #13919 opened by slaren
20m 49s sl/fix-ds-split
sl/fix-ds-split
20m 49s
cuda : prevent using split buffers with 3d/4d matrices Server #14590: Pull request #13919 opened by slaren
1h 0m 4s sl/fix-ds-split
sl/fix-ds-split
1h 0m 4s
cuda : prevent using split buffers with 3d/4d matrices CI #23196: Pull request #13919 opened by slaren
2h 25m 13s sl/fix-ds-split
sl/fix-ds-split
2h 25m 13s
cuda : prevent using split buffers with 3d/4d matrices Pull Request Labeler #11872: Pull request #13919 opened by slaren
1m 35s
1m 35s
llama : auto-batch preparation Server #14589: Pull request #13845 synchronize by ggerganov
45m 16s gg/auto-batch
gg/auto-batch
45m 16s
llama : auto-batch preparation CI #23195: Pull request #13845 synchronize by ggerganov
2h 20m 29s gg/auto-batch
gg/auto-batch
2h 20m 29s
llama : auto-batch Python check requirements.txt #3234: Commit ca69f32 pushed by ggerganov
18m 3s gg/auto-batch
gg/auto-batch
18m 3s
llama : auto-batch preparation Pull Request Labeler #11871: Pull request #13845 synchronize by ggerganov
4m 45s
4m 45s
ProTip! You can narrow down the results and go further in time using created:<2025-05-30 or the other filters available.