text-generation-webui/requirements_noavx2.txt

accelerate==0.27.*
colorama
datasets
einops
gradio==3.50.*
hqq==0.1.3.post1
jinja2==3.1.2
lm_eval==0.3.0
markdown
numpy==1.26.*
optimum==1.17.*
pandas
peft==0.8.*
Pillow>=9.5.0
pyyaml
requests
rich
safetensors==0.4.*
scipy
sentencepiece
tensorboard
transformers==4.38.*
tqdm
wandb

# API
SpeechRecognition==3.10.0
flask_cloudflared==0.0.14
sse-starlette==1.6.5
tiktoken

# bitsandbytes
bitsandbytes==0.42.*; platform_system != "Windows"
https://github.com/oobabooga/bitsandbytes-windows-webui/releases/download/wheels/bitsandbytes-0.42.0-py3-none-win_amd64.whl; platform_system == "Windows"

# llama-cpp-python (CPU only, no AVX2)
https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.55+cpuavx-cp311-cp311-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.55+cpuavx-cp310-cp310-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"
https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.55+cpuavx-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.55+cpuavx-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10"

# llama-cpp-python (CUDA, no tensor cores)
https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda-0.2.55+cu121avx-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda-0.2.55+cu121avx-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10"
https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda-0.2.55+cu121avx-cp311-cp311-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda-0.2.55+cu121avx-cp310-cp310-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"

# llama-cpp-python (CUDA, tensor cores)
https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda_tensorcores-0.2.55+cu121avx-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda_tensorcores-0.2.55+cu121avx-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10"
https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda_tensorcores-0.2.55+cu121avx-cp311-cp311-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda_tensorcores-0.2.55+cu121avx-cp310-cp310-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"

# CUDA wheels
https://github.com/jllllll/AutoGPTQ/releases/download/v0.6.0/auto_gptq-0.6.0+cu121-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
https://github.com/jllllll/AutoGPTQ/releases/download/v0.6.0/auto_gptq-0.6.0+cu121-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10"
https://github.com/jllllll/AutoGPTQ/releases/download/v0.6.0/auto_gptq-0.6.0+cu121-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
https://github.com/jllllll/AutoGPTQ/releases/download/v0.6.0/auto_gptq-0.6.0+cu121-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"
https://github.com/oobabooga/exllamav2/releases/download/v0.0.14.1/exllamav2-0.0.14.1+cu121-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
https://github.com/oobabooga/exllamav2/releases/download/v0.0.14.1/exllamav2-0.0.14.1+cu121-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10"
https://github.com/oobabooga/exllamav2/releases/download/v0.0.14.1/exllamav2-0.0.14.1+cu121-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
https://github.com/oobabooga/exllamav2/releases/download/v0.0.14.1/exllamav2-0.0.14.1+cu121-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"
https://github.com/oobabooga/exllamav2/releases/download/v0.0.14.1/exllamav2-0.0.14.1-py3-none-any.whl; platform_system == "Linux" and platform_machine != "x86_64"
https://github.com/oobabooga/flash-attention/releases/download/v2.5.6/flash_attn-2.5.6+cu122torch2.2.0cxx11abiFALSE-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
https://github.com/oobabooga/flash-attention/releases/download/v2.5.6/flash_attn-2.5.6+cu122torch2.2.0cxx11abiFALSE-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10"
https://github.com/Dao-AILab/flash-attention/releases/download/v2.5.6/flash_attn-2.5.6+cu122torch2.2cxx11abiFALSE-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
https://github.com/Dao-AILab/flash-attention/releases/download/v2.5.6/flash_attn-2.5.6+cu122torch2.2cxx11abiFALSE-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"
https://github.com/jllllll/GPTQ-for-LLaMa-CUDA/releases/download/0.1.1/gptq_for_llama-0.1.1+cu121-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
https://github.com/jllllll/GPTQ-for-LLaMa-CUDA/releases/download/0.1.1/gptq_for_llama-0.1.1+cu121-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10"
https://github.com/jllllll/GPTQ-for-LLaMa-CUDA/releases/download/0.1.1/gptq_for_llama-0.1.1+cu121-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
https://github.com/jllllll/GPTQ-for-LLaMa-CUDA/releases/download/0.1.1/gptq_for_llama-0.1.1+cu121-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"
https://github.com/jllllll/ctransformers-cuBLAS-wheels/releases/download/AVX/ctransformers-0.2.27+cu121-py3-none-any.whl
autoawq==0.1.8; platform_system == "Linux" or platform_system == "Windows"
Update accelerate requirement from ==0.25.* to ==0.27.* (#5546) 2024-02-19 23:14:04 +01:00			`accelerate==0.27.*`
Create alternative requirements.txt with AMD and Metal wheels (#4052) 2023-09-24 14:58:29 +02:00			`colorama`
			`datasets`
			`einops`
Revert gradio to 3.50.2 (#5513) 2024-02-16 00:40:23 +01:00			`gradio==3.50.*`
Bump hqq from 0.1.3 to 0.1.3.post1 (#5582) 2024-02-27 00:51:39 +01:00			`hqq==0.1.3.post1`
Add requirement jinja2==3.1.* to fix error as described in issue #5240 (#5249) --------- Co-authored-by: oobabooga <112222186+oobabooga@users.noreply.github.com> Co-authored-by: Rim <anonymous@mail.com> 2024-01-14 01:47:13 +01:00			`jinja2==3.1.2`
Pin lm_eval package version 2023-12-24 18:22:31 +01:00			`lm_eval==0.3.0`
Create alternative requirements.txt with AMD and Metal wheels (#4052) 2023-09-24 14:58:29 +02:00			`markdown`
Update numpy requirement from ==1.24.* to ==1.26.* (#5490) 2024-02-13 20:26:35 +01:00			`numpy==1.26.*`
Update optimum requirement from ==1.16.* to ==1.17.* (#5548) 2024-02-19 23:15:21 +01:00			`optimum==1.17.*`
Create alternative requirements.txt with AMD and Metal wheels (#4052) 2023-09-24 14:58:29 +02:00			`pandas`
Update peft requirement from ==0.7.* to ==0.8.* (#5446) 2024-02-13 20:27:18 +01:00			`peft==0.8.*`
Create alternative requirements.txt with AMD and Metal wheels (#4052) 2023-09-24 14:58:29 +02:00			`Pillow>=9.5.0`
			`pyyaml`
			`requests`
Add rich requirement 2023-12-20 06:58:36 +01:00			`rich`
Bump safetensors version 2024-02-05 03:40:25 +01:00			`safetensors==0.4.*`
Create alternative requirements.txt with AMD and Metal wheels (#4052) 2023-09-24 14:58:29 +02:00			`scipy`
			`sentencepiece`
			`tensorboard`
Fix transformers requirement 2024-03-03 19:49:28 +01:00			`transformers==4.38.*`
Create alternative requirements.txt with AMD and Metal wheels (#4052) 2023-09-24 14:58:29 +02:00			`tqdm`
			`wandb`

Do not install extensions requirements by default (#5621) 2024-03-04 08:46:39 +01:00			`# API`
			`SpeechRecognition==3.10.0`
			`flask_cloudflared==0.0.14`
			`sse-starlette==1.6.5`
			`tiktoken`

Create alternative requirements.txt with AMD and Metal wheels (#4052) 2023-09-24 14:58:29 +02:00			`# bitsandbytes`
Bump bitsandbytes to 0.42 (Linux only) 2024-02-16 19:47:39 +01:00			`bitsandbytes==0.42.*; platform_system != "Windows"`
Bump bitsandytes to 0.42.0 on Windows 2024-03-03 22:19:27 +01:00			`https://github.com/oobabooga/bitsandbytes-windows-webui/releases/download/wheels/bitsandbytes-0.42.0-py3-none-win_amd64.whl; platform_system == "Windows"`
Create alternative requirements.txt with AMD and Metal wheels (#4052) 2023-09-24 14:58:29 +02:00
Revert "Bump llama-cpp-python to 0.2.18 (#4611)" This reverts commit 923c8e25fb9d55fbf392cb07f7ddab1e0ee2b718. 2023-11-17 14:14:25 +01:00			`# llama-cpp-python (CPU only, no AVX2)`
Bump llama-cpp-python to 0.2.55 2024-03-03 21:14:48 +01:00			`https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.55+cpuavx-cp311-cp311-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"`
			`https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.55+cpuavx-cp310-cp310-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"`
			`https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.55+cpuavx-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"`
			`https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.55+cpuavx-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10"`
Revert "Bump llama-cpp-python to 0.2.18 (#4611)" This reverts commit 923c8e25fb9d55fbf392cb07f7ddab1e0ee2b718. 2023-11-17 14:14:25 +01:00
Add llama-cpp-python wheels with tensor cores support (#5003) 2023-12-19 21:30:53 +01:00			`# llama-cpp-python (CUDA, no tensor cores)`
Bump llama-cpp-python to 0.2.55 2024-03-03 21:14:48 +01:00			`https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda-0.2.55+cu121avx-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"`
			`https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda-0.2.55+cu121avx-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10"`
			`https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda-0.2.55+cu121avx-cp311-cp311-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"`
			`https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda-0.2.55+cu121avx-cp310-cp310-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"`
Add llama-cpp-python wheels with tensor cores support (#5003) 2023-12-19 21:30:53 +01:00
			`# llama-cpp-python (CUDA, tensor cores)`
Bump llama-cpp-python to 0.2.55 2024-03-03 21:14:48 +01:00			`https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda_tensorcores-0.2.55+cu121avx-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"`
			`https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda_tensorcores-0.2.55+cu121avx-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10"`
			`https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda_tensorcores-0.2.55+cu121avx-cp311-cp311-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"`
			`https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda_tensorcores-0.2.55+cu121avx-cp310-cp310-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"`
Add llama-cpp-python wheels with tensor cores support (#5003) 2023-12-19 21:30:53 +01:00
Create alternative requirements.txt with AMD and Metal wheels (#4052) 2023-09-24 14:58:29 +02:00			`# CUDA wheels`
Bump AutoGPTQ to 0.6.0 (adds Mixtral support) 2023-12-15 15:18:49 +01:00			`https://github.com/jllllll/AutoGPTQ/releases/download/v0.6.0/auto_gptq-0.6.0+cu121-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"`
			`https://github.com/jllllll/AutoGPTQ/releases/download/v0.6.0/auto_gptq-0.6.0+cu121-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10"`
			`https://github.com/jllllll/AutoGPTQ/releases/download/v0.6.0/auto_gptq-0.6.0+cu121-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"`
			`https://github.com/jllllll/AutoGPTQ/releases/download/v0.6.0/auto_gptq-0.6.0+cu121-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"`
Update PyTorch to 2.2 (also update flash-attn to 2.5.6) (#5618) 2024-03-03 23:40:32 +01:00			`https://github.com/oobabooga/exllamav2/releases/download/v0.0.14.1/exllamav2-0.0.14.1+cu121-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"`
			`https://github.com/oobabooga/exllamav2/releases/download/v0.0.14.1/exllamav2-0.0.14.1+cu121-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10"`
			`https://github.com/oobabooga/exllamav2/releases/download/v0.0.14.1/exllamav2-0.0.14.1+cu121-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"`
			`https://github.com/oobabooga/exllamav2/releases/download/v0.0.14.1/exllamav2-0.0.14.1+cu121-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"`
			`https://github.com/oobabooga/exllamav2/releases/download/v0.0.14.1/exllamav2-0.0.14.1-py3-none-any.whl; platform_system == "Linux" and platform_machine != "x86_64"`
			`https://github.com/oobabooga/flash-attention/releases/download/v2.5.6/flash_attn-2.5.6+cu122torch2.2.0cxx11abiFALSE-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"`
			`https://github.com/oobabooga/flash-attention/releases/download/v2.5.6/flash_attn-2.5.6+cu122torch2.2.0cxx11abiFALSE-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10"`
			`https://github.com/Dao-AILab/flash-attention/releases/download/v2.5.6/flash_attn-2.5.6+cu122torch2.2cxx11abiFALSE-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"`
			`https://github.com/Dao-AILab/flash-attention/releases/download/v2.5.6/flash_attn-2.5.6+cu122torch2.2cxx11abiFALSE-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"`
Add flash-attention 2 for windows (#4235) 2023-10-21 08:46:23 +02:00			`https://github.com/jllllll/GPTQ-for-LLaMa-CUDA/releases/download/0.1.1/gptq_for_llama-0.1.1+cu121-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"`
			`https://github.com/jllllll/GPTQ-for-LLaMa-CUDA/releases/download/0.1.1/gptq_for_llama-0.1.1+cu121-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10"`
			`https://github.com/jllllll/GPTQ-for-LLaMa-CUDA/releases/download/0.1.1/gptq_for_llama-0.1.1+cu121-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"`
			`https://github.com/jllllll/GPTQ-for-LLaMa-CUDA/releases/download/0.1.1/gptq_for_llama-0.1.1+cu121-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"`
			`https://github.com/jllllll/ctransformers-cuBLAS-wheels/releases/download/AVX/ctransformers-0.2.27+cu121-py3-none-any.whl`
Revert "Bump autoawq from 0.1.8 to 0.2.2 (#5547)" This reverts commit d04fef6a07b9c0a599895cd5ce61bd43bca86de4. 2024-02-23 04:48:04 +01:00			`autoawq==0.1.8; platform_system == "Linux" or platform_system == "Windows"`