Skip to content
This repository has been archived by the owner on Oct 11, 2024. It is now read-only.

Commit

Permalink
fix a bug
Browse files Browse the repository at this point in the history
  • Loading branch information
dhuangnm authored and dhuangnm committed Jun 12, 2024
1 parent 6729285 commit 9d25265
Showing 1 changed file with 2 additions and 2 deletions.
4 changes: 2 additions & 2 deletions Dockerfile
Original file line number Diff line number Diff line change
Expand Up @@ -70,15 +70,15 @@ RUN apt-get update -y && \
RUN ldconfig /usr/local/cuda-12.4/compat/

# install nm-vllm wheel first, so that torch etc will be installed
ARG build_type="nightly"
ARG build_type="NIGHTLY"
ARG build_version="latest"
ENV INSTALL_TYPE=${build_type}
ENV INSTALL_VERSION=${build_version}
# UPSTREAM SYNC: Install nm-vllm with sparsity extras
# use nm pypi for now for testing
RUN --mount=type=bind,from=build \
--mount=type=cache,target=/root/.cache/pip \
if [ "${INSTALL_TYPE}" = "nightly" ]; then \
if [ "${INSTALL_TYPE}" = "NIGHTLY" ]; then \
if [ "${INSTALL_VERSION}" = "latest" ]; then \
pip install nm-vllm-nightly[sparse] --extra-index-url https://pypi.neuralmagic.com/simple; \
else \
Expand Down

0 comments on commit 9d25265

Please sign in to comment.