Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Fixing vllm build #6433

Merged
merged 4 commits into from
Oct 16, 2023
Merged

Fixing vllm build #6433

Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
1832c59
Fixing torch version for vllm
oandreeva-nv Oct 13, 2023
25277e7
Follow up
oandreeva-nv Oct 13, 2023
a0ffdd3
Fixed build
oandreeva-nv Oct 15, 2023
9209316
Added JIRA ticket
oandreeva-nv Oct 16, 2023
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 3 additions & 1 deletion build.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1366,9 +1366,11 @@ def dockerfile_prepare_container_linux(argmap, backends, enable_gpu, target_mach
if "vllm" in backends:
# [DLIS-5606] Build Conda environment for vLLM backend
# Remove Pip install once vLLM backend moves to Conda environment.
# [DLIS-5650] Pre-installing torch 2.0.1, since vllm 0.2
# requires torch >= 2.0.0, but it doesn't work with torch 2.1.0.
df += """
# vLLM needed for vLLM backend
RUN pip3 install vllm=={}
RUN pip3 install torch==2.0.1 vllm=={}
""".format(
TRITON_VERSION_MAP[FLAGS.version][7]
)
Expand Down
Loading