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.