1 Star 0 Fork 0

lklake/TensorRT-LLM

加入 Gitee
与超过 1200万 开发者一起发现、参与优秀开源项目,私有仓库也完全免费 :)
免费加入
文件
克隆/下载
requirements.txt 631 Bytes
一键复制 编辑 原始数据 按行查看 历史
Kaiyu Xie 提交于 2024-06-04 20:26 . Update TensorRT-LLM (#1725)
--extra-index-url https://pypi.nvidia.com
accelerate>=0.25.0
build
colored
cuda-python # Do not override the custom version of cuda-python installed in the NGC PyTorch image.
diffusers>=0.27.0
lark
mpi4py
numpy<2
onnx>=1.12.0
polygraphy
psutil
pynvml>=11.5.0
pulp
pandas
h5py==3.10.0
StrEnum
sentencepiece>=0.1.99
tensorrt==10.0.1
# https://github.com/pytorch/pytorch/blob/v2.3.0/version.txt uses 2.3.0a0.
# https://docs.nvidia.com/deeplearning/frameworks/pytorch-release-notes/rel-24-04.html#rel-24-04 uses 2.3.0a0.
torch>=2.3.0a,<=2.3.0
nvidia-modelopt~=0.11,<0.12
transformers==4.40.2
wheel
optimum
evaluate
janus
mpmath>=1.3.0
马建仓 AI 助手
尝试更多
代码解读
代码找茬
代码优化
1
https://gitee.com/lklake/TensorRT-LLM.git
git@gitee.com:lklake/TensorRT-LLM.git
lklake
TensorRT-LLM
TensorRT-LLM
dependabot/pip/examples/multimodal/transformers-4.38.0

搜索帮助