Update ExLlamaV3 to 0.0.25

This commit is contained in:
oobabooga 2026-03-13 02:40:09 -07:00
parent c094bc943c
commit 5ddc1002d2

View file

@ -42,7 +42,7 @@ tiktoken
# CUDA wheels
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.91.0/llama_cpp_binaries-0.91.0+cu124-py3-none-win_amd64.whl; platform_system == "Windows"
https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.91.0/llama_cpp_binaries-0.91.0+cu124-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
https://github.com/turboderp-org/exllamav3/releases/download/v0.0.24/exllamav3-0.0.24+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/v0.0.24/exllamav3-0.0.24+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/turboderp-org/exllamav3/releases/download/v0.0.25/exllamav3-0.0.25+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/v0.0.25/exllamav3-0.0.25+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"