Skip to content

Bump exllamav2 to 0.0.4 and use pre-built wheels #4095

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
oobabooga merged 1 commit into from
Sep 27, 2023
Merged

Bump exllamav2 to 0.0.4 and use pre-built wheels #4095

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 3 additions & 1 deletion requirements.txt
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -8,7 +8,7 @@ accelerate==0.23.*
colorama
datasets
einops
exllamav2==0.0.3
exllamav2==0.0.4; platform_system != "Darwin" and platform_machine != "x86_64"
markdown
numpy==1.24
optimum==1.13.1
Expand Down Expand Up @@ -38,6 +38,8 @@ https://github.com/PanQiWei/AutoGPTQ/releases/download/v0.4.2/auto_gptq-0.4.2+cu
https://github.com/PanQiWei/AutoGPTQ/releases/download/v0.4.2/auto_gptq-0.4.2+cu117-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+cu117-cp310-cp310-win_amd64.whl; platform_system == "Windows"
https://github.com/jllllll/exllama/releases/download/0.0.17/exllama-0.0.17+cu117-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
https://github.com/turboderp/exllamav2/releases/download/v0.0.4/exllamav2-0.0.4+cu117-cp310-cp310-win_amd64.whl; platform_system == "Windows"
Copy link
Copy Markdown
Owner

@oobabooga oobabooga Sep 27, 2023

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Out of curiosity, why is a and platform_machine == "x86_64" not needed here? Also, can this line and line 11 apply simultaneously?

Copy link
Copy Markdown
Contributor Author

@jllllll jllllll Sep 27, 2023 •
edited
Loading

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Glad you caught that. I forgot that Windows uses amd64 instead of x86_64 for some reason.

This line will need and platform_machine == "amd64" and line 11 will need and platform_machine != "amd64"
This will also need to be applied to requirements_noavx2.txt.
That said, I think the wheel may take precedence as it is specified later in the file. I'm testing that now.

Edit: Just tested it and, fortunately, it does use the wheel. May need the conditions anyway just to ensure it doesn't stop working in the future.

It seems to prefer the wheel simply because it sees 0.0.4+cu117 as a newer version to 0.0.4.

https://github.com/turboderp/exllamav2/releases/download/v0.0.4/exllamav2-0.0.4+cu117-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/textgen-webui/llama_cpp_python_cuda-0.2.6+cu117-cp310-cp310-win_amd64.whl; platform_system == "Windows"
https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda-0.2.6+cu117-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/0.1.0/gptq_for_llama-0.1.0+cu117-cp310-cp310-win_amd64.whl; platform_system == "Windows"
Expand Down
2 changes: 1 addition & 1 deletion requirements_amd.txt
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -8,7 +8,7 @@ accelerate==0.23.*
colorama
datasets
einops
exllamav2==0.0.3
exllamav2==0.0.4
markdown
numpy==1.24
optimum==1.13.1
Expand Down
2 changes: 1 addition & 1 deletion requirements_amd_noavx2.txt
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -8,7 +8,7 @@ accelerate==0.23.*
colorama
datasets
einops
exllamav2==0.0.3
exllamav2==0.0.4
markdown
numpy==1.24
optimum==1.13.1
Expand Down
2 changes: 1 addition & 1 deletion requirements_apple_intel.txt
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -8,7 +8,7 @@ accelerate==0.23.*
colorama
datasets
einops
exllamav2==0.0.3
exllamav2==0.0.4
markdown
numpy==1.24
optimum==1.13.1
Expand Down
2 changes: 1 addition & 1 deletion requirements_apple_silicon.txt
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -8,7 +8,7 @@ accelerate==0.23.*
colorama
datasets
einops
exllamav2==0.0.3
exllamav2==0.0.4
markdown
numpy==1.24
optimum==1.13.1
Expand Down
2 changes: 1 addition & 1 deletion requirements_cpu_only.txt
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -8,7 +8,7 @@ accelerate==0.23.*
colorama
datasets
einops
exllamav2==0.0.3
exllamav2==0.0.4
markdown
numpy==1.24
optimum==1.13.1
Expand Down
2 changes: 1 addition & 1 deletion requirements_cpu_only_noavx2.txt
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -8,7 +8,7 @@ accelerate==0.23.*
colorama
datasets
einops
exllamav2==0.0.3
exllamav2==0.0.4
markdown
numpy==1.24
optimum==1.13.1
Expand Down
4 changes: 3 additions & 1 deletion requirements_noavx2.txt
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -8,7 +8,7 @@ accelerate==0.23.*
colorama
datasets
einops
exllamav2==0.0.3
exllamav2==0.0.4; platform_system != "Darwin" and platform_machine != "x86_64"
markdown
numpy==1.24
optimum==1.13.1
Expand Down Expand Up @@ -38,6 +38,8 @@ https://github.com/PanQiWei/AutoGPTQ/releases/download/v0.4.2/auto_gptq-0.4.2+cu
https://github.com/PanQiWei/AutoGPTQ/releases/download/v0.4.2/auto_gptq-0.4.2+cu117-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+cu117-cp310-cp310-win_amd64.whl; platform_system == "Windows"
https://github.com/jllllll/exllama/releases/download/0.0.17/exllama-0.0.17+cu117-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
https://github.com/turboderp/exllamav2/releases/download/v0.0.4/exllamav2-0.0.4+cu117-cp310-cp310-win_amd64.whl; platform_system == "Windows"
https://github.com/turboderp/exllamav2/releases/download/v0.0.4/exllamav2-0.0.4+cu117-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/textgen-webui/llama_cpp_python_cuda-0.2.6+cu117-cp310-cp310-win_amd64.whl; platform_system == "Windows"
https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda-0.2.6+cu117-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/0.1.0/gptq_for_llama-0.1.0+cu117-cp310-cp310-win_amd64.whl; platform_system == "Windows"
Expand Down
2 changes: 1 addition & 1 deletion requirements_nowheels.txt
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -8,7 +8,7 @@ accelerate==0.23.*
colorama
datasets
einops
exllamav2==0.0.3
exllamav2==0.0.4
markdown
numpy==1.24
optimum==1.13.1
Expand Down