Skip to content

Actions: ggml-org/llama.cpp

Actions

All workflows

Actions

Loading...
Loading

Showing runs from all workflows
21,397 workflow run results
21,397 workflow run results

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

metal: Copy kernels for quant to F32 conversions (#10976). EditorConfig Checker #22062: Pull request #12017 synchronize by gcp
21s gcp:cpy_metal_quants
gcp:cpy_metal_quants
21s
metal: Copy kernels for quant to F32 conversions (#10976). Server #11063: Pull request #12017 synchronize by gcp
8m 4s gcp:cpy_metal_quants
gcp:cpy_metal_quants
8m 4s
metal: Copy kernels for quant to F32 conversions (#10976). Pull Request Labeler #8402: Pull request #12017 synchronize by gcp
8m 13s
8m 13s
metal: Copy kernels for quant to F32 conversions (#10976). EditorConfig Checker #22061: Pull request #12017 opened by gcp
4m 2s gcp:cpy_metal_quants
gcp:cpy_metal_quants
4m 2s
metal: Copy kernels for quant to F32 conversions (#10976). CI #19659: Pull request #12017 opened by gcp
35m 56s gcp:cpy_metal_quants
gcp:cpy_metal_quants
35m 56s
metal: Copy kernels for quant to F32 conversions (#10976). Server #11062: Pull request #12017 opened by gcp
12m 42s gcp:cpy_metal_quants
gcp:cpy_metal_quants
12m 42s
metal: Copy kernels for quant to F32 conversions (#10976). Pull Request Labeler #8401: Pull request #12017 opened by gcp
23s
23s
cuda: Add Q5_1, Q5_0, Q4_1 and Q4_0 to F32 conversion support. (#10976) EditorConfig Checker #22060: Pull request #12000 synchronize by gcp
19s gcp:cpy_cuda_quants
gcp:cpy_cuda_quants
19s
cuda: Add Q5_1, Q5_0, Q4_1 and Q4_0 to F32 conversion support. (#10976) CI #19658: Pull request #12000 synchronize by gcp
34m 23s gcp:cpy_cuda_quants
gcp:cpy_cuda_quants
34m 23s
cuda: Add Q5_1, Q5_0, Q4_1 and Q4_0 to F32 conversion support. (#10976) Server #11061: Pull request #12000 synchronize by gcp
4m 38s gcp:cpy_cuda_quants
gcp:cpy_cuda_quants
4m 38s
cuda: Add Q5_1, Q5_0, Q4_1 and Q4_0 to F32 conversion support. (#10976) Pull Request Labeler #8400: Pull request #12000 synchronize by gcp
13s
13s
cuda: Add Q5_1, Q5_0, Q4_1 and Q4_0 to F32 conversion support. (#10976) Pull Request Labeler #8399: Pull request #12000 synchronize by gcp
11s
11s
vulkan: matmul dequantization improvements CI #19656: Pull request #12015 opened by netrunnereve
39m 50s vulkan_mm
vulkan_mm
39m 50s
vulkan: matmul dequantization improvements EditorConfig Checker #22058: Pull request #12015 opened by netrunnereve
17s vulkan_mm
vulkan_mm
17s
vulkan: matmul dequantization improvements Server #11059: Pull request #12015 opened by netrunnereve
7m 50s vulkan_mm
vulkan_mm
7m 50s
vulkan: matmul dequantization improvements Pull Request Labeler #8398: Pull request #12015 opened by netrunnereve
13s
13s
CUDA: optimize FA for GQA + large batches CI #19655: Pull request #12014 opened by JohannesGaessler
46m 7s JohannesGaessler:cuda-fa-mma-23
JohannesGaessler:cuda-fa-mma-23
46m 7s
CUDA: optimize FA for GQA + large batches Server #11058: Pull request #12014 opened by JohannesGaessler
8m 58s JohannesGaessler:cuda-fa-mma-23
JohannesGaessler:cuda-fa-mma-23
8m 58s
CUDA: optimize FA for GQA + large batches EditorConfig Checker #22057: Pull request #12014 opened by JohannesGaessler
19s JohannesGaessler:cuda-fa-mma-23
JohannesGaessler:cuda-fa-mma-23
19s
CUDA: optimize FA for GQA + large batches flake8 Lint #17499: Pull request #12014 opened by JohannesGaessler
21s JohannesGaessler:cuda-fa-mma-23
JohannesGaessler:cuda-fa-mma-23
21s
CUDA: optimize FA for GQA + large batches Python Type-Check #1882: Pull request #12014 opened by JohannesGaessler
1m 9s JohannesGaessler:cuda-fa-mma-23
JohannesGaessler:cuda-fa-mma-23
1m 9s
CUDA: optimize FA for GQA + large batches Pull Request Labeler #8397: Pull request #12014 opened by JohannesGaessler
17s
17s
cuda: Add Q5_1, Q5_0, Q4_1 and Q4_0 to F32 conversion support. (#10976) Pull Request Labeler #8396: Pull request #12000 synchronize by gcp
2m 9s
2m 9s
cuda: Add Q5_1, Q5_0, Q4_1 and Q4_0 to F32 conversion support. (#10976) Pull Request Labeler #8395: Pull request #12000 synchronize by gcp
2m 7s
2m 7s
cuda: Add Q5_1, Q5_0, Q4_1 and Q4_0 to F32 conversion support. (#10976) Pull Request Labeler #8394: Pull request #12000 synchronize by gcp
2m 3s
2m 3s
ProTip! You can narrow down the results and go further in time using created:<2025-02-21 or the other filters available.