Skip to content

Actions: ggml-org/llama.cpp

Actions

All workflows

Actions

Loading...
Loading

Showing runs from all workflows
38,047 workflow run results
38,047 workflow run results

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

feat: Hybrid unified/recurrent cache CI #23044: Pull request #13276 synchronize by gabe-l-hart
54m 24s gabe-l-hart:HybridCache
gabe-l-hart:HybridCache
54m 24s
feat: Hybrid unified/recurrent cache Server #14441: Pull request #13276 synchronize by gabe-l-hart
10m 21s gabe-l-hart:HybridCache
gabe-l-hart:HybridCache
10m 21s
feat: Hybrid unified/recurrent cache EditorConfig Checker #25896: Pull request #13276 synchronize by gabe-l-hart
18s gabe-l-hart:HybridCache
gabe-l-hart:HybridCache
18s
feat: Hybrid unified/recurrent cache Pull Request Labeler #11709: Pull request #13276 synchronize by gabe-l-hart
13s
13s
convert: handle when model's tokenization method relies on Mecab Pull Request Labeler #11708: Pull request #13830 synchronize by huydt84
11s
11s
ggml: improve ggml_backend_cuda_cpy_tensor_async Pull Request Labeler #11707: Pull request #13818 synchronize by koush
12s
12s
ggml: improve ggml_backend_cuda_cpy_tensor_async Pull Request Labeler #11706: Pull request #13818 synchronize by koush
14s
14s
convert : fix tensor naming conflict for llama 4 vision flake8 Lint #18296: Pull request #13836 synchronize by ngxson
17s ngxson:xsn/convert_fix_llama4_clash
ngxson:xsn/convert_fix_llama4_clash
17s
convert : fix tensor naming conflict for llama 4 vision EditorConfig Checker #25892: Pull request #13836 synchronize by ngxson
19s ngxson:xsn/convert_fix_llama4_clash
ngxson:xsn/convert_fix_llama4_clash
19s
convert : fix tensor naming conflict for llama 4 vision Python Type-Check #2804: Pull request #13836 synchronize by ngxson
1m 55s ngxson:xsn/convert_fix_llama4_clash
ngxson:xsn/convert_fix_llama4_clash
1m 55s
convert : fix tensor naming conflict for llama 4 vision Python check requirements.txt #3175: Pull request #13836 synchronize by ngxson
4m 17s ngxson:xsn/convert_fix_llama4_clash
ngxson:xsn/convert_fix_llama4_clash
4m 17s
convert : fix tensor naming conflict for llama 4 vision Pull Request Labeler #11705: Pull request #13836 synchronize by ngxson
12s
12s
convert : fix tensor naming conflict for llama 4 vision flake8 Lint #18295: Pull request #13836 opened by ngxson
19s ngxson:xsn/convert_fix_llama4_clash
ngxson:xsn/convert_fix_llama4_clash
19s
convert : fix tensor naming conflict for llama 4 vision EditorConfig Checker #25891: Pull request #13836 opened by ngxson
20s ngxson:xsn/convert_fix_llama4_clash
ngxson:xsn/convert_fix_llama4_clash
20s
convert : fix tensor naming conflict for llama 4 vision Python Type-Check #2803: Pull request #13836 opened by ngxson
1m 30s ngxson:xsn/convert_fix_llama4_clash
ngxson:xsn/convert_fix_llama4_clash
1m 30s
convert : fix tensor naming conflict for llama 4 vision Python check requirements.txt #3174: Pull request #13836 opened by ngxson
3m 14s ngxson:xsn/convert_fix_llama4_clash
ngxson:xsn/convert_fix_llama4_clash
3m 14s
convert : fix tensor naming conflict for llama 4 vision Pull Request Labeler #11704: Pull request #13836 opened by ngxson
14s
14s
opencl: add new ops - argsort, div, sub, addrows, sigmoid, … CI #23041: Commit a3c3084 pushed by max-krasnyansky
1h 13m 54s master
master
1h 13m 54s
opencl: add new ops - argsort, div, sub, addrows, sigmoid, … Release #167: Commit a3c3084 pushed by max-krasnyansky
35m 51s master
master
35m 51s
opencl: add new ops - argsort, div, sub, addrows, sigmoid, … Server #14438: Commit a3c3084 pushed by max-krasnyansky
16m 11s master
master
16m 11s
opencl: add new ops - argsort, div, sub, addrows, sigmoid, … EditorConfig Checker #25890: Commit a3c3084 pushed by max-krasnyansky
1m 57s master
master
1m 57s
opencl: mark mul_mat f32f32 as supporting non-contiguous tensors … CI #23040: Commit 1701d4c pushed by max-krasnyansky
47m 33s master
master
47m 33s
opencl: mark mul_mat f32f32 as supporting non-contiguous tensors … EditorConfig Checker #25889: Commit 1701d4c pushed by max-krasnyansky
19s master
master
19s
opencl: mark mul_mat f32f32 as supporting non-contiguous tensors … Release #166: Commit 1701d4c pushed by max-krasnyansky
28m 53s master
master
28m 53s
opencl: mark mul_mat f32f32 as supporting non-contiguous tensors … Server #14437: Commit 1701d4c pushed by max-krasnyansky
15m 42s master
master
15m 42s