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 16, 10:45 UTC
[CI/Build] Update Dockerfile install+deploy image to ubuntu 22.04 (#9130)
Co-authored-by: DarkLight1337 <tlleungac@connect.ust.hk>
Michael Goin committed
Oct 9, 2024 at 14:51 UTC
d5fbb8706d2c7fd00b64cff2efbe7c771fe82c3c
1 file changed
+1
-1
Dockerfile
+1
-1
@@ -144,7 +144,7 @@ RUN --mount=type=cache,target=/root/.cache/pip \
144
#################### DEV IMAGE ####################
145
#################### vLLM installation IMAGE ####################
146
# image with vLLM installed
147
-FROM nvidia/cuda:${CUDA_VERSION}-base-ubuntu20.04 AS vllm-base
147
+FROM nvidia/cuda:${CUDA_VERSION}-base-ubuntu22.04 AS vllm-base
148
ARG CUDA_VERSION=12.4.1
149
ARG PYTHON_VERSION=3.12
150
WORKDIR /vllm-workspace