Skip to content

Actions: ggml-org/llama.cpp

Actions

All workflows

Actions

Loading...
Loading

Showing runs from all workflows
26,981 workflow run results
26,981 workflow run results

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

PR: Refine ggml-hexagon backend(Qualcomm Hexagon NPU backend) for latest ggml,whisper.cpp,llama.cpp EditorConfig Checker #23058: Pull request #12326 synchronize by jeffzhou2000
1m 32s jeffzhou2000:pr_to_upstream
jeffzhou2000:pr_to_upstream
1m 32s
PR: Refine ggml-hexagon backend(Qualcomm Hexagon NPU backend) for latest ggml,whisper.cpp,llama.cpp Pull Request Labeler #9257: Pull request #12326 synchronize by jeffzhou2000
1m 11s
1m 11s
Vulkan: Remove dedicated aligned matrix matrix multiplication shaders EditorConfig Checker #23057: Pull request #12515 synchronize by 0cc4m
16s 0cc4m/vulkan-mm-remove-aligned
0cc4m/vulkan-mm-remove-aligned
16s
Vulkan: Remove dedicated aligned matrix matrix multiplication shaders Server #11962: Pull request #12515 synchronize by 0cc4m
10m 23s 0cc4m/vulkan-mm-remove-aligned
0cc4m/vulkan-mm-remove-aligned
10m 23s
Vulkan: Remove dedicated aligned matrix matrix multiplication shaders CI #20567: Pull request #12515 synchronize by 0cc4m
46m 18s 0cc4m/vulkan-mm-remove-aligned
0cc4m/vulkan-mm-remove-aligned
46m 18s
Vulkan: Remove dedicated aligned matrix matrix multiplication shaders Pull Request Labeler #9256: Pull request #12515 synchronize by 0cc4m
9s
9s
Vulkan: Remove dedicated aligned matrix matrix multiplication shaders Pull Request Labeler #9255: Pull request #12515 opened by 0cc4m
9s
9s
ggml : fix quantized cpy op (#12310) CI #20566: Commit ba932df pushed by ggerganov
48m 9s master
master
48m 9s
ggml : fix quantized cpy op (#12310) EditorConfig Checker #23056: Commit ba932df pushed by ggerganov
18s master
master
18s
ggml : fix quantized cpy op (#12310) Server #11961: Commit ba932df pushed by ggerganov
8m 23s master
master
8m 23s
llama-tts : precompute irFFT theta CI #20565: Pull request #12514 opened by marcoStocchi
40m 9s marcoStocchi:tts-fft
marcoStocchi:tts-fft
40m 9s
llama-tts : precompute irFFT theta Server #11960: Pull request #12514 opened by marcoStocchi
11m 37s marcoStocchi:tts-fft
marcoStocchi:tts-fft
11m 37s
llama-tts : precompute irFFT theta EditorConfig Checker #23055: Pull request #12514 opened by marcoStocchi
16s marcoStocchi:tts-fft
marcoStocchi:tts-fft
16s
llama-tts : precompute irFFT theta Pull Request Labeler #9254: Pull request #12514 opened by marcoStocchi
11s
11s
musa: refine compute capability (#12493) CI #20564: Commit fac63a3 pushed by JohannesGaessler
47m 9s master
master
47m 9s
musa: refine compute capability (#12493) EditorConfig Checker #23054: Commit fac63a3 pushed by JohannesGaessler
16s master
master
16s
musa: refine compute capability (#12493) Server #11959: Commit fac63a3 pushed by JohannesGaessler
8m 10s master
master
8m 10s
vulkan: Optimize mul_mat_vec p021 and nc shaders (#12505) Server #11958: Commit eddfb43 pushed by 0cc4m
10m 37s master
master
10m 37s
vulkan: Optimize mul_mat_vec p021 and nc shaders (#12505) CI #20563: Commit eddfb43 pushed by 0cc4m
43m 22s master
master
43m 22s
vulkan: Optimize mul_mat_vec p021 and nc shaders (#12505) EditorConfig Checker #23053: Commit eddfb43 pushed by 0cc4m
16s master
master
16s
perplexity: Add option to ignore context window overflow errors and continue score calculation Pull Request Labeler #9253: Pull request #12512 opened by EAddario
10s
10s
quantize: Handle user-defined quantization levels for additional tensors Pull Request Labeler #9252: Pull request #12511 opened by EAddario
11s
11s
quantize: Handle user-defined quantization levels for additional tensors EditorConfig Checker #23051: Pull request #12511 opened by EAddario
26s EAddario:quantize
EAddario:quantize
26s
quantize: Handle user-defined quantization levels for additional tensors CI #20561: Pull request #12511 opened by EAddario
35m 10s EAddario:quantize
EAddario:quantize
35m 10s
quantize: Handle user-defined quantization levels for additional tensors Server #11956: Pull request #12511 opened by EAddario
3m 28s EAddario:quantize
EAddario:quantize
3m 28s