text-generation-webui/requirements_noavx2.txt

accelerate==0.27.*
aqlm[gpu,cpu]==1.1.3; platform_system == "Linux"
bitsandbytes==0.43.*
colorama
datasets
einops
gradio==4.26.*
hqq==0.1.5
jinja2==3.1.2
lm_eval==0.3.0
markdown
numba==0.59.*
numpy==1.26.*
optimum==1.17.*
pandas
peft==0.8.*
Pillow>=9.5.0
psutil
pyyaml
requests
rich
safetensors==0.4.*
scipy
sentencepiece
tensorboard
transformers==4.40.*
tqdm
wandb

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

# llama-cpp-python (CPU only, no AVX2)
https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.61+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-0.2.61+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-0.2.61+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-0.2.61+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-0.2.61+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-0.2.61+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-0.2.61+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-0.2.61+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-0.2.61+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-0.2.61+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-0.2.61+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-0.2.61+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/turboderp/exllamav2/releases/download/v0.0.19/exllamav2-0.0.19+cu121-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
https://github.com/turboderp/exllamav2/releases/download/v0.0.19/exllamav2-0.0.19+cu121-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10"
https://github.com/turboderp/exllamav2/releases/download/v0.0.19/exllamav2-0.0.19+cu121-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
https://github.com/turboderp/exllamav2/releases/download/v0.0.19/exllamav2-0.0.19+cu121-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"
https://github.com/turboderp/exllamav2/releases/download/v0.0.19/exllamav2-0.0.19-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"
autoawq==0.2.3; platform_system == "Linux" or platform_system == "Windows"
Update accelerate requirement from ==0.25.* to ==0.27.* (#5546) 2024-02-19 17:14:04 -05:00			`accelerate==0.27.*`
Bump aqlm[cpu,gpu] from 1.1.2 to 1.1.3 (#5790) 2024-04-05 12:26:49 -04:00			`aqlm[gpu,cpu]==1.1.3; platform_system == "Linux"`
Bump bitsandbytes to 0.43, add official Windows wheel 2024-03-10 11:30:53 -04:00			`bitsandbytes==0.43.*`
Create alternative requirements.txt with AMD and Metal wheels (#4052) 2023-09-24 08:58:29 -04:00			`colorama`
			`datasets`
			`einops`
Update gradio requirement from ==4.25.* to ==4.26.* (#5832) 2024-04-11 01:24:53 -04:00			`gradio==4.26.*`
Bump HQQ to 0.1.5 2024-03-05 05:33:51 -05:00			`hqq==0.1.5`
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> 2024-01-13 19:47:13 -05:00			`jinja2==3.1.2`
Pin lm_eval package version 2023-12-24 12:22:31 -05:00			`lm_eval==0.3.0`
Create alternative requirements.txt with AMD and Metal wheels (#4052) 2023-09-24 08:58:29 -04:00			`markdown`
Add numba to requirements.txt 2024-03-10 19:13:29 -04:00			`numba==0.59.*`
Update numpy requirement from ==1.24.* to ==1.26.* (#5490) 2024-02-13 14:26:35 -05:00			`numpy==1.26.*`
Update optimum requirement from ==1.16.* to ==1.17.* (#5548) 2024-02-19 17:15:21 -05:00			`optimum==1.17.*`
Create alternative requirements.txt with AMD and Metal wheels (#4052) 2023-09-24 08:58:29 -04:00			`pandas`
Revert "Update peft requirement from ==0.8.* to ==0.9.* (#5626)" This reverts commit 72a498ddd44a895205e53b5696742dc4ded9e12e. 2024-03-05 05:56:37 -05:00			`peft==0.8.*`
Create alternative requirements.txt with AMD and Metal wheels (#4052) 2023-09-24 08:58:29 -04:00			`Pillow>=9.5.0`
requirements: add psutil (#5819) 2024-04-06 22:02:20 -04:00			`psutil`
Create alternative requirements.txt with AMD and Metal wheels (#4052) 2023-09-24 08:58:29 -04:00			`pyyaml`
			`requests`
Add rich requirement 2023-12-20 00:58:36 -05:00			`rich`
Bump safetensors version 2024-02-04 21:40:25 -05:00			`safetensors==0.4.*`
Create alternative requirements.txt with AMD and Metal wheels (#4052) 2023-09-24 08:58:29 -04:00			`scipy`
			`sentencepiece`
			`tensorboard`
Bump transformers to 4.40 2024-04-18 18:55:34 -04:00			`transformers==4.40.*`
Create alternative requirements.txt with AMD and Metal wheels (#4052) 2023-09-24 08:58:29 -04:00			`tqdm`
			`wandb`

Do not install extensions requirements by default (#5621) 2024-03-04 02:46:39 -05:00			`# API`
			`SpeechRecognition==3.10.0`
			`flask_cloudflared==0.0.14`
Revert sse-starlette version bump because it breaks API request cancellation (#5873) 2024-04-18 14:05:00 -04:00			`sse-starlette==1.6.5`
Do not install extensions requirements by default (#5621) 2024-03-04 02:46:39 -05:00			`tiktoken`

Revert "Bump llama-cpp-python to 0.2.18 (#4611)" This reverts commit 923c8e25fb9d55fbf392cb07f7ddab1e0ee2b718. 2023-11-17 08:14:25 -05:00			`# llama-cpp-python (CPU only, no AVX2)`
Bump llama-cpp-python to 0.2.61 & fix the crash 2024-04-11 17:15:34 -04:00			`https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.61+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-0.2.61+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-0.2.61+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-0.2.61+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 08:14:25 -05:00
Add llama-cpp-python wheels with tensor cores support (#5003) 2023-12-19 15:30:53 -05:00			`# llama-cpp-python (CUDA, no tensor cores)`
Bump llama-cpp-python to 0.2.61 & fix the crash 2024-04-11 17:15:34 -04:00			`https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda-0.2.61+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-0.2.61+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-0.2.61+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-0.2.61+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 15:30:53 -05:00
			`# llama-cpp-python (CUDA, tensor cores)`
Bump llama-cpp-python to 0.2.61 & fix the crash 2024-04-11 17:15:34 -04:00			`https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda_tensorcores-0.2.61+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-0.2.61+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-0.2.61+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-0.2.61+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 15:30:53 -05:00
Create alternative requirements.txt with AMD and Metal wheels (#4052) 2023-09-24 08:58:29 -04:00			`# CUDA wheels`
Bump AutoGPTQ to 0.6.0 (adds Mixtral support) 2023-12-15 09:18:49 -05:00			`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"`
Bumped ExLlamaV2 to version 0.0.19 to resolve #5851 (#5880) 2024-04-19 18:04:40 -04:00			`https://github.com/turboderp/exllamav2/releases/download/v0.0.19/exllamav2-0.0.19+cu121-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"`
			`https://github.com/turboderp/exllamav2/releases/download/v0.0.19/exllamav2-0.0.19+cu121-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10"`
			`https://github.com/turboderp/exllamav2/releases/download/v0.0.19/exllamav2-0.0.19+cu121-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"`
			`https://github.com/turboderp/exllamav2/releases/download/v0.0.19/exllamav2-0.0.19+cu121-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"`
			`https://github.com/turboderp/exllamav2/releases/download/v0.0.19/exllamav2-0.0.19-py3-none-any.whl; platform_system == "Linux" and platform_machine != "x86_64"`
Update PyTorch to 2.2 (also update flash-attn to 2.5.6) (#5618) 2024-03-03 17:40:32 -05:00			`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 02:46:23 -04:00			`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"`
Add back AutoAWQ for Windows https://github.com/casper-hansen/AutoAWQ/issues/377#issuecomment-1986440695 2024-03-08 17:54:56 -05:00			`autoawq==0.2.3; platform_system == "Linux" or platform_system == "Windows"`