@tduncan / Nvidia-Optimization-Stack-VLLM Mirror · read-only / commits / d5fbb8706d
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 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