Skip to content

Actions: ggml-org/llama.cpp

Actions

All workflows

Actions

Loading...
Loading

Showing runs from all workflows
47,804 workflow run results
47,804 workflow run results

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

Adding a simple-function-call example - hopefully not doing anything wrong Pull Request Labeler #13832: Pull request #14682 synchronize by klogdotwebsitenotdotcom
12s
12s
CUDA: fix quantized KV cache + multiple sequences CI #25208: Pull request #14822 opened by JohannesGaessler
1h 2m 11s JohannesGaessler:cuda-fa-nc-quant
JohannesGaessler:cuda-fa-nc-quant
1h 2m 11s
CUDA: fix quantized KV cache + multiple sequences Server #16601: Pull request #14822 opened by JohannesGaessler
14m 1s JohannesGaessler:cuda-fa-nc-quant
JohannesGaessler:cuda-fa-nc-quant
14m 1s
CUDA: fix quantized KV cache + multiple sequences Pull Request Labeler #13831: Pull request #14822 opened by JohannesGaessler
17s
17s
finetune: SGD optimizer, more CLI args EditorConfig Checker #28257: Pull request #13873 synchronize by graehl
20s graehl:finelayer
graehl:finelayer
20s
finetune: SGD optimizer, more CLI args Server #16600: Pull request #13873 synchronize by graehl
11m 36s graehl:finelayer
graehl:finelayer
11m 36s
finetune: SGD optimizer, more CLI args CI #25207: Pull request #13873 synchronize by graehl
1h 1m 27s graehl:finelayer
graehl:finelayer
1h 1m 27s
finetune: SGD optimizer, more CLI args Pull Request Labeler #13830: Pull request #13873 synchronize by graehl
13s
13s
cuda : fix multi-seq, quantized FA Server #16599: Pull request #14820 opened by ggerganov
17m 43s gg/fix-fa-q-non-cont
gg/fix-fa-q-non-cont
17m 43s
cuda : fix multi-seq, quantized FA CI #25206: Pull request #14820 opened by ggerganov
1h 9m 26s gg/fix-fa-q-non-cont
gg/fix-fa-q-non-cont
1h 9m 26s
cuda : fix multi-seq, quantized FA Pull Request Labeler #13829: Pull request #14820 opened by ggerganov
44s
44s
metal: SSM_SCAN performance Server #16598: Pull request #14743 synchronize by gabe-l-hart
12m 31s gabe-l-hart:GraniteFourPerf
gabe-l-hart:GraniteFourPerf
12m 31s
metal: SSM_SCAN performance EditorConfig Checker #28256: Pull request #14743 synchronize by gabe-l-hart
20s gabe-l-hart:GraniteFourPerf
gabe-l-hart:GraniteFourPerf
20s
metal: SSM_SCAN performance CI #25205: Pull request #14743 synchronize by gabe-l-hart
55m 46s gabe-l-hart:GraniteFourPerf
gabe-l-hart:GraniteFourPerf
55m 46s
metal: SSM_SCAN performance Pull Request Labeler #13828: Pull request #14743 synchronize by gabe-l-hart
12s
12s
gguf: use an unordered_map for faster duplicate tensor name lookups Pull Request Labeler #13827: Pull request #14818 synchronize by struct
12s
12s
metal: SSM_SCAN performance EditorConfig Checker #28255: Pull request #14743 synchronize by gabe-l-hart
20s gabe-l-hart:GraniteFourPerf
gabe-l-hart:GraniteFourPerf
20s
metal: SSM_SCAN performance CI #25204: Pull request #14743 synchronize by gabe-l-hart
44m 22s gabe-l-hart:GraniteFourPerf
gabe-l-hart:GraniteFourPerf
44m 22s
metal: SSM_SCAN performance Server #16597: Pull request #14743 synchronize by gabe-l-hart
11m 56s gabe-l-hart:GraniteFourPerf
gabe-l-hart:GraniteFourPerf
11m 56s
metal: SSM_SCAN performance Pull Request Labeler #13826: Pull request #14743 synchronize by gabe-l-hart
13s
13s
[WIP]backend: Integrating QNN (Qualcomm AI Engine Direct) as a dedicated backend for Qualcomm NPUs Pull Request Labeler #13825: Pull request #12063 synchronize by chraac
6m 45s
6m 45s
CUDA: add fused rms norm EditorConfig Checker #28253: Pull request #14800 synchronize by am17an
17s am17an:cuda_fused_rms_norm
am17an:cuda_fused_rms_norm
17s
CUDA: add fused rms norm Server #16595: Pull request #14800 synchronize by am17an
14m 0s am17an:cuda_fused_rms_norm
am17an:cuda_fused_rms_norm
14m 0s
CUDA: add fused rms norm CI #25202: Pull request #14800 synchronize by am17an
1h 2m 1s am17an:cuda_fused_rms_norm
am17an:cuda_fused_rms_norm
1h 2m 1s
CUDA: add fused rms norm Pull Request Labeler #13824: Pull request #14800 synchronize by am17an
10s
10s