@tduncan / Nvidia-Optimization-Stack-VLLM Mirror · read-only / commits / f3e024bece
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, 05:30 UTC

[CI/CD] Upgrade PyTorch version to v2.1.1 (#2045)

Woosuk Kwon committed Dec 11, 2023 at 17:48 UTC f3e024bece5c6a5efb855903db227e0d375ad481
3 files changed +4 -4
.github/workflows/publish.yml
+1 -1
@@ -49,7 +49,7 @@ jobs:
49 matrix:
50 os: ['ubuntu-20.04']
51 python-version: ['3.8', '3.9', '3.10', '3.11']
52 - pytorch-version: ['2.1.0']
52 + pytorch-version: ['2.1.1']
53 cuda-version: ['11.8', '12.1']
54
55 steps:
pyproject.toml
+1 -1
@@ -4,7 +4,7 @@ requires = [
4 "ninja",
5 "packaging",
6 "setuptools >= 49.4.0",
7 - "torch >= 2.1.0",
7 + "torch >= 2.1.1",
8 "wheel",
9 ]
10 build-backend = "setuptools.build_meta"
requirements.txt
+2 -2
@@ -6,9 +6,9 @@ pyarrow # Required for Ray data.
6 sentencepiece # Required for LLaMA tokenizer.
7 numpy
8 einops # Required for phi-1_5
9 -torch >= 2.1.0
9 +torch >= 2.1.1
10 transformers >= 4.34.0 # Required for Mistral.
11 -xformers >= 0.0.22.post7 # Required for CUDA 12.1.
11 +xformers >= 0.0.23 # Required for CUDA 12.1.
12 fastapi
13 uvicorn[standard]
14 pydantic == 1.10.13 # Required for OpenAI server.