Skip to content

Actions: JamePeng/llama-cpp-python

Actions

All workflows

Actions

Loading...
Loading

Showing runs from all workflows
251 workflow runs
251 workflow runs

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

Add Pillow process code in _load_image which can reliably handle comm… Tests #315: Commit 3b01333 pushed by JamePeng
6m 53s main
main
6m 53s
Optimize: Initialize Jinja template in __init__ instead of __call__ t… Tests #314: Commit 30ace25 pushed by JamePeng
6m 25s main
main
6m 25s
Update pyproject.toml dependencies and requires-python>=3.9 Tests #313: Commit baa60ae pushed by JamePeng
9m 27s main
main
9m 27s
Build Wheels (CU128) for Windows(Basic) Build Wheels (CU128) for Windows(Basic) #1: Manually run by JamePeng
7h 58m 55s main
main
7h 58m 55s
Build Wheels (CU124-126) for Windows(Basic) Build Wheels (CU124-126) for Windows(Basic) #3: Manually run by JamePeng
8h 48m 24s main
main
8h 48m 24s
Build Wheels (CU128) for Windows Build Wheels (CU128) for Windows #16: Manually run by JamePeng
4h 13m 17s main
main
4h 13m 17s
Build Wheels (CU124-126) for Windows Build Wheels (CU124-126) for Windows #10: Manually run by JamePeng
6h 18m 50s main
main
6h 18m 50s
Build Wheels(CU128) for Linux Build Wheels(CU128) for Linux #28: Manually run by JamePeng
2h 27m 43s main
main
2h 27m 43s
Build Wheels(CU126) for Linux Build Wheels(CU126) for Linux #57: Manually run by JamePeng
1h 6m 7s main
main
1h 6m 7s
Build Wheels(CU124) for Linux Build Wheels(CU124) for Linux #57: Manually run by JamePeng
1h 4m 12s main
main
1h 4m 12s
Update Submodule vendor/llama.cpp cb623de..07b0e7a Tests #312: Commit 917cc0b pushed by JamePeng
6m 53s main
main
6m 53s
Update Llava15ChatHandler to accept use_gpu, image_min_tokens, an… Tests #311: Commit 47d098e pushed by JamePeng
6m 6s main
main
6m 6s
Update README.md Tests #310: Commit a32aa9e pushed by JamePeng
7m 2s main
main
7m 2s
Update Submodule vendor/llama.cpp c7b7db0..cb623de Tests #309: Commit c51b589 pushed by JamePeng
6m 23s main
main
6m 23s
Supplementing the use of mtmd_helper_log_set to align with llama.cpp Tests #308: Commit e0dbf82 pushed by JamePeng
7m 17s main
main
7m 17s
Remove parameters that are no longer needed: mctx_params.verbosity Tests #307: Commit 65eced9 pushed by JamePeng
6m 2s main
main
6m 2s
Update llama.cpp 20251115 and Move the ggml-related code to _ggml.py. Tests #306: Commit 77b1efb pushed by JamePeng
6m 16s main
main
6m 16s
Build Wheels (CU128) for Windows Build Wheels (CU128) for Windows #15: Manually run by JamePeng
5h 13m 31s main
main
5h 13m 31s
Build Wheels (CU124-126) for Windows(Basic) Build Wheels (CU124-126) for Windows(Basic) #2: Manually run by JamePeng
6h 3m 21s main
main
6h 3m 21s
Build Wheels (CU124-126) for Windows Build Wheels (CU124-126) for Windows #9: Manually run by JamePeng
5h 4m 14s main
main
5h 4m 14s
Build Wheels(CU128) for Linux Build Wheels(CU128) for Linux #27: Manually run by JamePeng
1h 28m 53s main
main
1h 28m 53s
Build Wheels(CU126) for Linux Build Wheels(CU126) for Linux #56: Manually run by JamePeng
1h 3m 32s main
main
1h 3m 32s
Build Wheels(CU124) for Linux Build Wheels(CU124) for Linux #56: Manually run by JamePeng
1h 1m 32s main
main
1h 1m 32s
Use httplib to download model from an URL when the libcurl is disabled Tests #302: Commit 4e901b7 pushed by JamePeng
6m 39s main
main
6m 39s
Fixed CMake Error at vendor/llama.cpp/tools/mtmd/CMakeLists.txt:16 (s… Tests #301: Commit 326a4f3 pushed by JamePeng
6m 27s main
main
6m 27s