Skip to content

Actions: JamePeng/llama-cpp-python

Actions

All workflows

Actions

Loading...
Loading

Showing runs from all workflows
213 workflow runs
213 workflow runs

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

Update README.md Tests #291: Commit 67baa01 pushed by JamePeng
13m 28s main
main
13m 28s
Merge pull request #17 from TAO71-AI/main Tests #289: Commit 17ba24f pushed by JamePeng
12m 41s main
main
12m 41s
Update llama.cpp API and supplementing the State/sessions API Tests #285: Commit a1c6dc2 pushed by JamePeng
11m 5s main
main
11m 5s
Update Submodule vendor/llama.cpp 48bd265..b7f9010 Tests #282: Commit 24d72de pushed by JamePeng
6m 40s main
main
6m 40s
Build Wheels (CU128) for Windows Build Wheels (CU128) for Windows #13: Manually run by JamePeng
4h 47m 46s main
main
4h 47m 46s
Build Wheels (CU124-126) for Windows Build Wheels (CU124-126) for Windows #7: Manually run by JamePeng
5h 8m 39s main
main
5h 8m 39s
Build Wheels(CU124) for Linux Build Wheels(CU124) for Linux #54: Manually run by JamePeng
58m 8s main
main
58m 8s
Build Wheels(CU126) for Linux Build Wheels(CU126) for Linux #54: Manually run by JamePeng
59m 20s main
main
59m 20s
Build Wheels(CU128) for Linux Build Wheels(CU128) for Linux #25: Manually run by JamePeng
1h 21m 52s main
main
1h 21m 52s
Sync llama/mtmd API change, support clip flash-attn Tests #280: Commit 6f8ec8b pushed by JamePeng
7m 2s main
main
7m 2s
Update Submodule vendor/llama.cpp 76af40a..070ff4d Tests #278: Commit 9a1c3a7 pushed by JamePeng
11m 31s main
main
11m 31s
Optimize Windows CUDA Wheel Build Workflow Tests #277: Commit c008d9e pushed by JamePeng
5m 58s main
main
5m 58s
Optimize Windows CU128 Wheel Build Workflow(Testing) Tests #276: Commit 68c5d45 pushed by JamePeng
6m 1s main
main
6m 1s
Update Submodule vendor/llama.cpp cf659bb..76af40a Tests #270: Commit 670c642 pushed by JamePeng
6m 56s main
main
6m 56s
Implement LlamaTrieCache into llama_cache.py: Optimize LlamaCache loo… Tests #269: Commit 2419dc2 pushed by JamePeng
7m 28s main
main
7m 28s
Sync model : Minimax M2 Tests #268: Commit d42cd32 pushed by JamePeng
6m 24s main
main
6m 24s
Update README.md for Qwen3VL example(Thinking/No Thinking) Tests #267: Commit ea4ca57 pushed by JamePeng
50m 22s main
main
50m 22s
Build Wheels (CU128) for Windows Build Wheels (CU128) for Windows #6: Manually run by JamePeng
3h 58m 1s main
main
3h 58m 1s
Build Wheels (CU124-126) for Windows Build Wheels (CU124-126) for Windows #6: Manually run by JamePeng
5h 43m 59s main
main
5h 43m 59s
Build Wheels(CU128) for Linux Build Wheels(CU128) for Linux #24: Manually run by JamePeng
1h 21m 17s main
main
1h 21m 17s
Build Wheels(CU126) for Linux Build Wheels(CU126) for Linux #53: Manually run by JamePeng
57m 49s main
main
57m 49s
Build Wheels(CU124) for Linux Build Wheels(CU124) for Linux #53: Manually run by JamePeng
56m 31s main
main
56m 31s
Update Submodule vendor/llama.cpp 16724b5..8da3c0e: Tests #266: Commit 5c34564 pushed by JamePeng
5m 14s main
main
5m 14s
Update Submodule vendor/llama.cpp 16724b5..8da3c0e: Tests #265: Commit 27df0ae pushed by JamePeng
6m 56s main
main
6m 56s
feat: Add Qwen3VLChatHandler into llama_chat_format.py Tests #264: Commit 33b31be pushed by JamePeng
5m 20s main
main
5m 20s