Skip to content

Actions: ggml-org/llama.cpp

Actions

All workflows

Actions

Loading...
Loading

Showing runs from all workflows
57,154 workflow run results
57,154 workflow run results

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

llama: use FA + max. GPU layers by default Pull Request Labeler #15465: Pull request #15434 synchronize by JohannesGaessler
11s
11s
sampling : optimize samplers by reusing bucket sort CI #26780: Pull request #15665 synchronize by ggerganov
1h 12m 50s gg/sampling-sort-opt
gg/sampling-sort-opt
1h 12m 50s
sampling : optimize samplers by reusing bucket sort EditorConfig Checker #30110: Pull request #15665 synchronize by ggerganov
4m 0s gg/sampling-sort-opt
gg/sampling-sort-opt
4m 0s
sampling : optimize samplers by reusing bucket sort Build on RISCV Linux Machine by Cloud-V #415: Pull request #15665 synchronize by ggerganov
4m 57s gg/sampling-sort-opt
gg/sampling-sort-opt
4m 57s
sampling : optimize samplers by reusing bucket sort Server #18200: Pull request #15665 synchronize by ggerganov
13m 1s gg/sampling-sort-opt
gg/sampling-sort-opt
13m 1s
sampling : optimize samplers by reusing bucket sort Pull Request Labeler #15464: Pull request #15665 synchronize by ggerganov
11s
11s
llama: use FA + max. GPU layers by default CI #26779: Pull request #15434 synchronize by JohannesGaessler
1h 27m 1s JohannesGaessler:llama-update-defaults
JohannesGaessler:llama-update-defaults
1h 27m 1s
llama: use FA + max. GPU layers by default flake8 Lint #19353: Pull request #15434 synchronize by JohannesGaessler
16s JohannesGaessler:llama-update-defaults
JohannesGaessler:llama-update-defaults
16s
llama: use FA + max. GPU layers by default EditorConfig Checker #30109: Pull request #15434 synchronize by JohannesGaessler
18s JohannesGaessler:llama-update-defaults
JohannesGaessler:llama-update-defaults
18s
llama: use FA + max. GPU layers by default Python Type-Check #4061: Pull request #15434 synchronize by JohannesGaessler
1m 35s JohannesGaessler:llama-update-defaults
JohannesGaessler:llama-update-defaults
1m 35s
llama: use FA + max. GPU layers by default Server #18199: Pull request #15434 synchronize by JohannesGaessler
12m 29s JohannesGaessler:llama-update-defaults
JohannesGaessler:llama-update-defaults
12m 29s
llama: use FA + max. GPU layers by default Build on RISCV Linux Machine by Cloud-V #414: Pull request #15434 synchronize by JohannesGaessler
6m 33s JohannesGaessler:llama-update-defaults
JohannesGaessler:llama-update-defaults
6m 33s
llama: use FA + max. GPU layers by default Pull Request Labeler #15463: Pull request #15434 synchronize by JohannesGaessler
12s
12s
CUDA: use FP32 arithmetic for conv2d CI #26778: Pull request #15683 opened by JohannesGaessler
1h 31m 56s JohannesGaessler:cuda-fix-compile
JohannesGaessler:cuda-fix-compile
1h 31m 56s
CUDA: use FP32 arithmetic for conv2d EditorConfig Checker #30108: Pull request #15683 opened by JohannesGaessler
27m 25s JohannesGaessler:cuda-fix-compile
JohannesGaessler:cuda-fix-compile
27m 25s
CUDA: use FP32 arithmetic for conv2d Server #18198: Pull request #15683 opened by JohannesGaessler
51m 44s JohannesGaessler:cuda-fix-compile
JohannesGaessler:cuda-fix-compile
51m 44s
CUDA: use FP32 arithmetic for conv2d Build on RISCV Linux Machine by Cloud-V #413: Pull request #15683 opened by JohannesGaessler
14m 25s JohannesGaessler:cuda-fix-compile
JohannesGaessler:cuda-fix-compile
14m 25s
CUDA: use FP32 arithmetic for conv2d Pull Request Labeler #15462: Pull request #15683 opened by JohannesGaessler
30m 5s
30m 5s
quantize: add option to automatically choose optimal quant types to reach a bpw target at lowest error Server #18197: Pull request #15550 synchronize by EAddario
57m 51s EAddario:quantize
EAddario:quantize
57m 51s
quantize: add option to automatically choose optimal quant types to reach a bpw target at lowest error CI #26777: Pull request #15550 synchronize by EAddario
1h 52m 37s EAddario:quantize
EAddario:quantize
1h 52m 37s
quantize: add option to automatically choose optimal quant types to reach a bpw target at lowest error EditorConfig Checker #30107: Pull request #15550 synchronize by EAddario
5m 6s EAddario:quantize
EAddario:quantize
5m 6s
quantize: add option to automatically choose optimal quant types to reach a bpw target at lowest error Build on RISCV Linux Machine by Cloud-V #412: Pull request #15550 synchronize by EAddario
24m 44s EAddario:quantize
EAddario:quantize
24m 44s
quantize: add option to automatically choose optimal quant types to reach a bpw target at lowest error Pull Request Labeler #15461: Pull request #15550 synchronize by EAddario
40m 58s
40m 58s
imatrix: calculate activation-based statistics for new format (GGUF) imatrices EditorConfig Checker #30106: Pull request #14891 synchronize by EAddario
38m 52s EAddario:imatrix
EAddario:imatrix
38m 52s
imatrix: calculate activation-based statistics for new format (GGUF) imatrices Server #18196: Pull request #14891 synchronize by EAddario
45m 52s EAddario:imatrix
EAddario:imatrix
45m 52s