Mirrors/text-generation-webui
1
0
Fork 0
mirror of https://github.com/oobabooga/text-generation-webui.git synced 2024-11-22 16:17:57 +01:00
Code Issues Packages Projects Releases Wiki Activity

Use Pytorch 2.1 exllama wheels (#4285)

Browse Source
This commit is contained in:
jllllll 2023-10-14 13:27:59 -05:00 committed by GitHub
parent cd1cad1b47
commit 1f5a2c5597
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
4 changed files with 6 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
requirements.txt
View File

@ -33,8 +33,8 @@ https://github.com/abetlen/llama-cpp-python/releases/download/v0.2.11/llama_cpp_
# CUDA wheels # CUDA wheels
https://github.com/jllllll/AutoGPTQ/releases/download/v0.4.2/auto_gptq-0.4.2+cu118-cp310-cp310-win_amd64.whl; platform_system == "Windows" https://github.com/jllllll/AutoGPTQ/releases/download/v0.4.2/auto_gptq-0.4.2+cu118-cp310-cp310-win_amd64.whl; platform_system == "Windows"
https://github.com/jllllll/AutoGPTQ/releases/download/v0.4.2/auto_gptq-0.4.2+cu118-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" https://github.com/jllllll/AutoGPTQ/releases/download/v0.4.2/auto_gptq-0.4.2+cu118-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
https://github.com/jllllll/exllama/releases/download/0.0.17/exllama-0.0.17+cu118-cp310-cp310-win_amd64.whl; platform_system == "Windows" https://github.com/jllllll/exllama/releases/download/0.0.18/exllama-0.0.18+cu118-cp310-cp310-win_amd64.whl; platform_system == "Windows"
https://github.com/jllllll/exllama/releases/download/0.0.17/exllama-0.0.17+cu118-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" https://github.com/jllllll/exllama/releases/download/0.0.18/exllama-0.0.18+cu118-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
https://github.com/turboderp/exllamav2/releases/download/v0.0.6/exllamav2-0.0.6+cu118-cp310-cp310-win_amd64.whl; platform_system == "Windows" https://github.com/turboderp/exllamav2/releases/download/v0.0.6/exllamav2-0.0.6+cu118-cp310-cp310-win_amd64.whl; platform_system == "Windows"
https://github.com/turboderp/exllamav2/releases/download/v0.0.6/exllamav2-0.0.6+cu118-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" https://github.com/turboderp/exllamav2/releases/download/v0.0.6/exllamav2-0.0.6+cu118-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
https://github.com/Dao-AILab/flash-attention/releases/download/v2.3.2/flash_attn-2.3.2+cu118torch2.1cxx11abiFALSE-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" https://github.com/Dao-AILab/flash-attention/releases/download/v2.3.2/flash_attn-2.3.2+cu118torch2.1cxx11abiFALSE-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"

2
requirements_amd.txt
View File

@ -32,6 +32,6 @@ https://github.com/abetlen/llama-cpp-python/releases/download/v0.2.11/llama_cpp_
# AMD wheels # AMD wheels
https://github.com/jllllll/AutoGPTQ/releases/download/v0.4.2/auto_gptq-0.4.2+rocm5.6-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" https://github.com/jllllll/AutoGPTQ/releases/download/v0.4.2/auto_gptq-0.4.2+rocm5.6-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
https://github.com/jllllll/exllama/releases/download/0.0.17/exllama-0.0.17+rocm5.6-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" https://github.com/jllllll/exllama/releases/download/0.0.18/exllama-0.0.18+rocm5.6-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/rocm/llama_cpp_python_cuda-0.2.11+rocm5.6.1-cp310-cp310-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/rocm/llama_cpp_python_cuda-0.2.11+rocm5.6.1-cp310-cp310-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
https://github.com/jllllll/GPTQ-for-LLaMa-CUDA/releases/download/0.1.1/gptq_for_llama-0.1.1+rocm5.6-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" https://github.com/jllllll/GPTQ-for-LLaMa-CUDA/releases/download/0.1.1/gptq_for_llama-0.1.1+rocm5.6-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"

2
requirements_amd_noavx2.txt
View File

@ -32,5 +32,5 @@ https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/
# AMD wheels # AMD wheels
https://github.com/jllllll/AutoGPTQ/releases/download/v0.4.2/auto_gptq-0.4.2+rocm5.6-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" https://github.com/jllllll/AutoGPTQ/releases/download/v0.4.2/auto_gptq-0.4.2+rocm5.6-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
https://github.com/jllllll/exllama/releases/download/0.0.17/exllama-0.0.17+rocm5.6-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" https://github.com/jllllll/exllama/releases/download/0.0.18/exllama-0.0.18+rocm5.6-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
https://github.com/jllllll/GPTQ-for-LLaMa-CUDA/releases/download/0.1.1/gptq_for_llama-0.1.1+rocm5.6-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" https://github.com/jllllll/GPTQ-for-LLaMa-CUDA/releases/download/0.1.1/gptq_for_llama-0.1.1+rocm5.6-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"

4
requirements_noavx2.txt
View File

@ -33,8 +33,8 @@ https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/
# CUDA wheels # CUDA wheels
https://github.com/jllllll/AutoGPTQ/releases/download/v0.4.2/auto_gptq-0.4.2+cu118-cp310-cp310-win_amd64.whl; platform_system == "Windows" https://github.com/jllllll/AutoGPTQ/releases/download/v0.4.2/auto_gptq-0.4.2+cu118-cp310-cp310-win_amd64.whl; platform_system == "Windows"
https://github.com/jllllll/AutoGPTQ/releases/download/v0.4.2/auto_gptq-0.4.2+cu118-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" https://github.com/jllllll/AutoGPTQ/releases/download/v0.4.2/auto_gptq-0.4.2+cu118-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
https://github.com/jllllll/exllama/releases/download/0.0.17/exllama-0.0.17+cu118-cp310-cp310-win_amd64.whl; platform_system == "Windows" https://github.com/jllllll/exllama/releases/download/0.0.18/exllama-0.0.18+cu118-cp310-cp310-win_amd64.whl; platform_system == "Windows"
https://github.com/jllllll/exllama/releases/download/0.0.17/exllama-0.0.17+cu118-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" https://github.com/jllllll/exllama/releases/download/0.0.18/exllama-0.0.18+cu118-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
https://github.com/turboderp/exllamav2/releases/download/v0.0.6/exllamav2-0.0.6+cu118-cp310-cp310-win_amd64.whl; platform_system == "Windows" https://github.com/turboderp/exllamav2/releases/download/v0.0.6/exllamav2-0.0.6+cu118-cp310-cp310-win_amd64.whl; platform_system == "Windows"
https://github.com/turboderp/exllamav2/releases/download/v0.0.6/exllamav2-0.0.6+cu118-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" https://github.com/turboderp/exllamav2/releases/download/v0.0.6/exllamav2-0.0.6+cu118-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
https://github.com/Dao-AILab/flash-attention/releases/download/v2.3.2/flash_attn-2.3.2+cu118torch2.1cxx11abiFALSE-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" https://github.com/Dao-AILab/flash-attention/releases/download/v2.3.2/flash_attn-2.3.2+cu118torch2.1cxx11abiFALSE-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"