Skip to content

chore: fix wideep h100 #2568

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 2 commits into from
Aug 21, 2025
Merged

chore: fix wideep h100 #2568

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
eb2eea4
widep
ishandhanani Aug 20, 2025
e49b747
bump
ishandhanani Aug 20, 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
2 changes: 1 addition & 1 deletion components/backends/sglang/docs/multinode-examples.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -78,7 +78,7 @@ python3 -m dynamo.sglang \

Node 4: Run the remaining 8 shards of the decode worker
```bash
python3 -m dynamo.sglang.decode_worker \
python3 -m dynamo.sglang \
--model-path /model/ \
--served-model-name deepseek-ai/DeepSeek-R1 \
--tp 16 \
Expand Down
2 changes: 1 addition & 1 deletion components/backends/sglang/slurm_jobs/scripts/h100.sh
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -156,7 +156,7 @@ elif [ "$mode" = "decode" ]; then
--deepep-mode low_latency \
--mem-fraction-static 0.835 \
--ep-num-redundant-experts 32 \
--cuda-graph-bs 256
--cuda-graph-bs 128
elif [ "$cmd" = "sglang" ]; then
# H100 sglang decode command
python3 -m sglang.launch_server \
Expand Down
2 changes: 1 addition & 1 deletion components/backends/sglang/slurm_jobs/scripts/worker_setup.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -261,7 +261,7 @@ def setup_head_prefill_node(prefill_host_ip: str) -> None:

logging.info(f"Starting ingress server on node {prefill_host_ip}")
ingress_process = run_command(
"dynamo run in=http out=dyn --http-port=8000", background=True
"python3 -m dynamo.frontend --http-port=8000", background=True
)
if not ingress_process:
raise RuntimeError("Failed to start ingress")
Expand Down
4 changes: 2 additions & 2 deletions container/Dockerfile.sglang-wideep
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -13,7 +13,7 @@
# See the License for the specific language governing permissions and
# limitations under the License.

ARG SGLANG_IMAGE_TAG="v0.5.0rc0-cu126"
ARG SGLANG_IMAGE_TAG="v0.5.0rc2-cu126"

FROM lmsysorg/sglang:${SGLANG_IMAGE_TAG}

Expand Down Expand Up @@ -97,7 +97,7 @@ RUN cd dynamo/lib/bindings/python && \
cd /sgl-workspace/dynamo && \
pip install --break-system-packages .

RUN pip install --break-system-packages sglang-router==0.1.5
RUN pip install --break-system-packages sglang-router==0.1.9

RUN wget --tries=3 --waitretry=5 \
https://github.com/nats-io/nats-server/releases/download/v2.10.28/\
Expand Down
Loading