@tduncan / Nvidia-Optimization-Stack-VLLM Mirror · read-only / commits / 6a6119554c
Fork 0

A high-throughput and memory-efficient inference and serving engine for LLMs

Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git

Synced Nov 17, 06:45 UTC

lock torch version to 2.0.1 (#1290)

yanxiyue committed Oct 11, 2023 at 00:21 UTC 6a6119554cee13bb4ef5018155be5530d6aaca26
2 files changed +3 -3
pyproject.toml
+1 -1
@@ -3,7 +3,7 @@ requires = [
3 "ninja",
4 "packaging",
5 "setuptools",
6 - "torch >= 2.0.0",
6 + "torch == 2.0.1",
7 "wheel",
8 ]
9 build-backend = "setuptools.build_meta"
requirements.txt
+2 -2
@@ -5,9 +5,9 @@ pandas # Required for Ray data.
5 pyarrow # Required for Ray data.
6 sentencepiece # Required for LLaMA tokenizer.
7 numpy
8 -torch >= 2.0.0
8 +torch == 2.0.1
9 transformers >= 4.33.1 # Required for Code Llama.
10 -xformers >= 0.0.22
10 +xformers == 0.0.22
11 fastapi
12 uvicorn[standard]
13 pydantic < 2 # Required for OpenAI server.