Switch flash-attn wheels from kingbri1 to mjun0812

This commit is contained in:
oobabooga
2026-05-07 14:15:09 -07:00
parent 3b9d0feedc
commit 95c0a261f5

View File

@@ -49,5 +49,5 @@ https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.126.0/ik_ll
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.126.0/ik_llama_cpp_binaries-0.126.0+cu124-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
https://github.com/turboderp-org/exllamav3/releases/download/v0.0.30/exllamav3-0.0.30+cu128.torch2.9.0-cp313-cp313-win_amd64.whl; platform_system == "Windows" and python_version == "3.13"
https://github.com/turboderp-org/exllamav3/releases/download/v0.0.30/exllamav3-0.0.30+cu128.torch2.9.0-cp313-cp313-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.13"
https://github.com/kingbri1/flash-attention/releases/download/v2.8.3/flash_attn-2.8.3+cu128torch2.9.0cxx11abiFALSE-cp313-cp313-win_amd64.whl; platform_system == "Windows" and python_version == "3.13"
https://github.com/kingbri1/flash-attention/releases/download/v2.8.3/flash_attn-2.8.3+cu128torch2.9.0cxx11abiFALSE-cp313-cp313-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.13"
https://github.com/mjun0812/flash-attention-prebuild-wheels/releases/download/v0.7.13/flash_attn-2.8.3+cu128torch2.9-cp313-cp313-win_amd64.whl; platform_system == "Windows" and python_version == "3.13"
https://github.com/mjun0812/flash-attention-prebuild-wheels/releases/download/v0.9.0/flash_attn-2.8.3+cu128torch2.9-cp313-cp313-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.13"