Skip to content

chore: bump sgl and update dp attn yaml #1362

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
merged 1 commit into from
Jun 3, 2025
Merged

chore: bump sgl and update dp attn yaml #1362

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
5 changes: 3 additions & 2 deletions container/Dockerfile.sglang
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -136,8 +136,9 @@ RUN if [ "$ARCH" = "arm64" ]; then \

# Install sglang
# Once either 0.4.6post6 or 0.4.7 is released, we can switch back to using the published version
# This commit references a fix for DP attention and NIXL https://github.com/sgl-project/sglang/pull/6473
ARG SGLANG_COMMIT="e806f708c954020bda7d1cc98035a44fd6a4eb96"
# This commit references multiple perf fixes for DP attention and NIXL https://github.com/sgl-project/sglang/pull/6780
# 6/2(ishan) - moving to ToT for performance purposes
ARG SGLANG_COMMIT="6376b632eb4daef306b89ede0eabdcb89ddff728"
RUN --mount=type=cache,target=/root/.cache/uv \
git clone https://github.com/sgl-project/sglang.git && \
cd sglang && \
Expand Down
2 changes: 1 addition & 1 deletion examples/sglang/configs/disagg-dp-attention.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -14,7 +14,7 @@
# limitations under the License.

Frontend:
served_model_name: deepseek-ai/DeepSeek-R1-Distill-Llama-8B
served_model_name: silence09/DeepSeek-R1-Small-2layers
endpoint: dynamo.SGLangWorker.generate
port: 8000

Expand Down
Loading