mirror of
https://github.com/oobabooga/text-generation-webui.git
synced 2026-01-06 16:50:11 +01:00
54 lines
3.3 KiB
Plaintext
54 lines
3.3 KiB
Plaintext
accelerate==1.5.*
|
|
bitsandbytes==0.45.*
|
|
colorama
|
|
datasets
|
|
einops
|
|
fastapi==0.112.4
|
|
gradio==4.37.*
|
|
jinja2==3.1.6
|
|
markdown
|
|
numba==0.59.*
|
|
numpy==1.26.*
|
|
pandas
|
|
peft==0.15.*
|
|
Pillow>=9.5.0
|
|
psutil
|
|
pydantic==2.8.2
|
|
pyyaml
|
|
requests
|
|
rich
|
|
safetensors==0.5.*
|
|
scipy
|
|
sentencepiece
|
|
tensorboard
|
|
transformers==4.50.*
|
|
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-0.3.8+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-0.3.8+cpuavx2-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
|
|
|
|
# llama-cpp-python (CUDA, with GGML_CUDA_FORCE_MMQ)
|
|
https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda-0.3.8+cu124-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-0.3.8+cu124-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
|
|
|
|
# llama-cpp-python (CUDA, without GGML_CUDA_FORCE_MMQ)
|
|
https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda_tensorcores-0.3.8+cu124-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-0.3.8+cu124-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
|
|
|
|
# CUDA wheels
|
|
https://github.com/oobabooga/exllamav3/releases/download/v0.0.1/exllamav3-0.0.1+cu124.torch2.6.0-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
|
|
https://github.com/oobabooga/exllamav3/releases/download/v0.0.1/exllamav3-0.0.1+cu124.torch2.6.0-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/v0.2.8/exllamav2-0.2.8+cu124.torch2.6.0-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
|
|
https://github.com/oobabooga/exllamav2/releases/download/v0.2.8/exllamav2-0.2.8+cu124.torch2.6.0-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/v0.2.8/exllamav2-0.2.8-py3-none-any.whl; platform_system == "Linux" and platform_machine != "x86_64"
|
|
https://github.com/oobabooga/flash-attention/releases/download/v2.7.4.post1/flash_attn-2.7.4.post1+cu124torch2.6.0cxx11abiFALSE-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
|
|
https://github.com/Dao-AILab/flash-attention/releases/download/v2.7.4.post1/flash_attn-2.7.4.post1+cu12torch2.6cxx11abiFALSE-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
|