Skip to content

chore: fix install #2191

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

Merged
dmitry-tokarev-nv merged 3 commits into from
Jul 30, 2025
Merged

chore: fix install #2191

Show file tree
Hide file tree
Changes from 1 commit
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
d9b5f4a
test
ishandhanani Jul 30, 2025
a22a2b9
fix(container): update pip install commands in Dockerfiles to use cor…
ishandhanani Jul 30, 2025
1ef96d0
fix: add separate pre release install for flashinfer-python
nv-anants Jul 30, 2025
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
Prev Previous commit
fix: add separate pre release install for flashinfer-python
  • Loading branch information
@nv-anants
nv-anants committed Jul 30, 2025
commit 1ef96d02b0155508114b92a2bb73dca93a68df92
7 changes: 6 additions & 1 deletion README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -167,10 +167,15 @@ To specify which GPUs to use set environment variable `CUDA_VISIBLE_DEVICES`.

## SGLang


```
# Install libnuma
# Install libnuma-dev
apt install -y libnuma-dev

# Install flashinfer-python pre-release (required by sglang for optimized inference)
uv pip install "flashinfer-python==0.2.9rc2" --prerelease=allow

# Install ai-dynamo with sglang support
uv pip install ai-dynamo[sglang]
```

Expand Down
9 changes: 4 additions & 5 deletions container/Dockerfile.sglang
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -378,8 +378,6 @@ RUN --mount=type=bind,source=./container/launch_message.txt,target=/workspace/la
sed '/^#\s/d' /workspace/launch_message.txt > ~/.launch_screen && \
echo "cat ~/.launch_screen" >> ~/.bashrc

ENV PYTHONPATH=/workspace/dynamo/components/planner/src:/workspace/examples/sglang/utils:$PYTHONPATH

########################################
########## Development Image ###########
########################################
Expand Down Expand Up @@ -446,7 +444,10 @@ RUN apt-get update && \
COPY --from=ci_minimum /workspace/target/release/metrics /usr/local/bin/metrics
COPY --from=wheel_builder /workspace/dist/*.whl wheelhouse/
COPY --from=base /workspace/wheels/nixl/*.whl wheelhouse/
RUN uv pip install "ai-dynamo[sglang]" --pre --find-links wheelhouse

# Install flashinfer-python pre-release version separately, then install ai-dynamo with sglang support
RUN uv pip install "flashinfer-python==0.2.9rc2" --prerelease=allow && \
uv pip install "ai-dynamo[sglang]" --find-links wheelhouse

# Copy launch banner
RUN --mount=type=bind,source=./container/launch_message.txt,target=/workspace/launch_message.txt \
Expand All @@ -466,7 +467,5 @@ RUN uv pip install /workspace/benchmarks
# Copy attribution files
COPY ATTRIBUTION* LICENSE /workspace/

ENV PYTHONPATH=/workspace/examples/sglang/utils:$PYTHONPATH

ENTRYPOINT ["/opt/nvidia/nvidia_entrypoint.sh"]
CMD []
Loading