text-generation-webui/requirements.txt

accelerate==1.2.*
bitsandbytes==0.45.*
colorama
datasets
einops
fastapi==0.112.4
gradio==4.37.*
jinja2==3.1.4
markdown
numba==0.59.*
numpy==1.26.*
pandas
peft==0.12.*
Pillow>=9.5.0
psutil
pydantic==2.8.2
pyyaml
requests
rich
safetensors==0.4.*
scipy
sentencepiece
tensorboard
transformers==4.47.*
tqdm
wandb

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

# llama-cpp-python (CPU only, AVX2)
https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.3.5+cpuavx2-cp311-cp311-linux_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-0.3.5+cpuavx2-cp310-cp310-linux_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-0.3.5+cpuavx2-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-0.3.5+cpuavx2-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-0.3.5+cu121-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-0.3.5+cu121-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-0.3.5+cu121-cp311-cp311-linux_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-0.3.5+cu121-cp310-cp310-linux_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-0.3.5+cu121-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-0.3.5+cu121-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-0.3.5+cu121-cp311-cp311-linux_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-0.3.5+cu121-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"

# CUDA wheels
https://github.com/oobabooga/exllamav2/releases/download/v0.2.7/exllamav2-0.2.7+cu121.torch2.4.1-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
https://github.com/oobabooga/exllamav2/releases/download/v0.2.7/exllamav2-0.2.7+cu121.torch2.4.1-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10"
https://github.com/oobabooga/exllamav2/releases/download/v0.2.7/exllamav2-0.2.7+cu121.torch2.4.1-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/v0.2.7/exllamav2-0.2.7+cu121.torch2.4.1-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/v0.2.7/exllamav2-0.2.7-py3-none-any.whl; platform_system == "Linux" and platform_machine != "x86_64"
https://github.com/oobabooga/flash-attention/releases/download/v2.7.2.post1/flash_attn-2.7.2.post1+cu122torch2.4.1cxx11abiFALSE-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
https://github.com/oobabooga/flash-attention/releases/download/v2.7.2.post1/flash_attn-2.7.2.post1+cu122torch2.4.1cxx11abiFALSE-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10"
https://github.com/Dao-AILab/flash-attention/releases/download/v2.7.2.post1/flash_attn-2.7.2.post1+cu12torch2.4cxx11abiFALSE-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/v2.7.2.post1/flash_attn-2.7.2.post1+cu12torch2.4cxx11abiFALSE-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"
Update accelerate requirement from ==1.1.* to ==1.2.* (#6583) 2024-12-16 18:58:50 -03:00			`accelerate==1.2.*`
Update bitsandbytes requirement from ==0.44.* to ==0.45.* (#6584) 2024-12-16 19:48:51 -03:00			`bitsandbytes==0.45.*`
Add 4-bit LoRA support (#1200) 2023-04-16 23:26:52 -03:00			`colorama`
New yaml character format (#337 from TheTerrasque/feature/yaml-characters) This doesn't break backward compatibility with JSON characters. 2023-04-03 01:34:25 +02:00			`datasets`
Falcon support (trust-remote-code and autogptq checkboxes) (#2367) --------- Co-authored-by: oobabooga <112222186+oobabooga@users.noreply.github.com> 2023-05-29 08:20:18 -05:00			`einops`
Pin fastapi/pydantic requirement versions 2024-09-06 18:38:39 -07:00			`fastapi==0.112.4`
Improved UI (#6575) 2024-12-17 00:47:41 -03:00			`gradio==4.37.*`
Bump jinja2 from 3.1.2 to 3.1.4 (#6172) 2024-06-27 21:12:39 -03:00			`jinja2==3.1.4`
Sort the requirements 2023-03-15 12:40:03 -03:00			`markdown`
Add numba to requirements.txt 2024-03-10 16:13:29 -07:00			`numba==0.59.*`
Update numpy requirement from ==1.24.* to ==1.26.* (#5490) 2024-02-13 16:26:35 -03:00			`numpy==1.26.*`
Add an "Evaluate" tab to calculate the perplexities of models (#1322) 2023-04-21 00:20:33 -03:00			`pandas`
Update peft requirement from ==0.8.* to ==0.12.* (#6292) 2024-08-19 23:33:56 -03:00			`peft==0.12.*`
Add Pillow as a requirement 2023-04-08 18:48:46 -03:00			`Pillow>=9.5.0`
requirements: add psutil (#5819) 2024-04-06 22:02:20 -04:00			`psutil`
Pin fastapi/pydantic requirement versions 2024-09-06 18:38:39 -07:00			`pydantic==2.8.2`
Add an "Evaluate" tab to calculate the perplexities of models (#1322) 2023-04-21 00:20:33 -03:00			`pyyaml`
Add requests to requirements.txt 2023-03-11 14:47:30 -03:00			`requests`
Add rich requirement 2023-12-19 21:58:36 -08:00			`rich`
Bump safetensors version 2024-02-04 18:40:25 -08:00			`safetensors==0.4.*`
Add 'scipy' to requirements.txt #2335 (#2343) Unlisted dependency of bitsandbytes 2023-05-25 21:26:25 -05:00			`scipy`
Add CUDA wheels for llama-cpp-python by jllllll 2023-07-19 19:31:19 -07:00			`sentencepiece`
Add Tensorboard/Weights and biases integration for training (#2624) 2023-07-12 17:53:31 +03:00			`tensorboard`
Bump transformers to 4.47 2024-12-09 07:00:15 -08:00			`transformers==4.47.*`
Add CUDA wheels for llama-cpp-python by jllllll 2023-07-19 19:31:19 -07:00			`tqdm`
			`wandb`
Pin aiofiles version to fix statvfs issue 2023-08-09 08:07:55 -07:00
Do not install extensions requirements by default (#5621) 2024-03-04 04:46:39 -03:00			`# 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 23:35:00 +05:30			`sse-starlette==1.6.5`
Do not install extensions requirements by default (#5621) 2024-03-04 04:46:39 -03:00			`tiktoken`

Add back my llama-cpp-python wheels, bump to 0.2.65 (#5964) 2024-04-30 09:11:31 -03:00			`# llama-cpp-python (CPU only, AVX2)`
Bump llama-cpp-python to 0.3.5, remove macos 12 wheels (workflow is failing) 2024-12-11 07:14:59 -08:00			`https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.3.5+cpuavx2-cp311-cp311-linux_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-0.3.5+cpuavx2-cp310-cp310-linux_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-0.3.5+cpuavx2-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-0.3.5+cpuavx2-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10"`
Add back my llama-cpp-python wheels, bump to 0.2.65 (#5964) 2024-04-30 09:11:31 -03:00
			`# llama-cpp-python (CUDA, no tensor cores)`
Bump llama-cpp-python to 0.3.5, remove macos 12 wheels (workflow is failing) 2024-12-11 07:14:59 -08:00			`https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda-0.3.5+cu121-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-0.3.5+cu121-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-0.3.5+cu121-cp311-cp311-linux_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-0.3.5+cu121-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"`
Bump llama-cpp-python to 0.2.83, add back tensorcore wheels Also add back the progress bar patch 2024-07-22 18:05:11 -07:00
			`# llama-cpp-python (CUDA, tensor cores)`
Bump llama-cpp-python to 0.3.5, remove macos 12 wheels (workflow is failing) 2024-12-11 07:14:59 -08:00			`https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda_tensorcores-0.3.5+cu121-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-0.3.5+cu121-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-0.3.5+cu121-cp311-cp311-linux_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-0.3.5+cu121-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"`
Add back my llama-cpp-python wheels, bump to 0.2.65 (#5964) 2024-04-30 09:11:31 -03:00
Create alternative requirements.txt with AMD and Metal wheels (#4052) 2023-09-24 09:58:29 -03:00			`# CUDA wheels`
Bump ExLlamaV2 to 0.2.7 2024-12-30 04:31:10 -08:00			`https://github.com/oobabooga/exllamav2/releases/download/v0.2.7/exllamav2-0.2.7+cu121.torch2.4.1-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"`
			`https://github.com/oobabooga/exllamav2/releases/download/v0.2.7/exllamav2-0.2.7+cu121.torch2.4.1-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10"`
			`https://github.com/oobabooga/exllamav2/releases/download/v0.2.7/exllamav2-0.2.7+cu121.torch2.4.1-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/v0.2.7/exllamav2-0.2.7+cu121.torch2.4.1-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/v0.2.7/exllamav2-0.2.7-py3-none-any.whl; platform_system == "Linux" and platform_machine != "x86_64"`
Bump flash-attention to v2.7.2.post1 2024-12-09 10:17:17 -08:00			`https://github.com/oobabooga/flash-attention/releases/download/v2.7.2.post1/flash_attn-2.7.2.post1+cu122torch2.4.1cxx11abiFALSE-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"`
			`https://github.com/oobabooga/flash-attention/releases/download/v2.7.2.post1/flash_attn-2.7.2.post1+cu122torch2.4.1cxx11abiFALSE-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10"`
			`https://github.com/Dao-AILab/flash-attention/releases/download/v2.7.2.post1/flash_attn-2.7.2.post1+cu12torch2.4cxx11abiFALSE-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/v2.7.2.post1/flash_attn-2.7.2.post1+cu12torch2.4cxx11abiFALSE-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"`