Skip to content

chore: typo and new commands (#3617) #3625

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
saturley-hall merged 1 commit into from
Oct 14, 2025
Merged

chore: typo and new commands (#3617) #3625

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
2 changes: 1 addition & 1 deletion components/backends/sglang/deploy/disagg.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -61,7 +61,7 @@ spec:
image: nvcr.io/nvidia/ai-dynamo/sglang-runtime:0.6.0
workingDir: /workspace/components/backends/sglang
command:
- python3E
- python3
- -m
- dynamo.sglang
args:
Expand Down
8 changes: 2 additions & 6 deletions components/backends/sglang/launch/disagg_dp_attn.sh
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -16,10 +16,6 @@ trap cleanup EXIT INT TERM
python3 -m dynamo.frontend --http-port=8000 &
DYNAMO_PID=$!

# Set the expert distribution recording directory
mkdir -p /tmp/sglang_expert_distribution_record
export SGLANG_EXPERT_DISTRIBUTION_RECORDER_DIR=/tmp/sglang_expert_distribution_record

# run prefill worker
python3 -m dynamo.sglang \
--model-path silence09/DeepSeek-R1-Small-2layers \
Expand All @@ -31,7 +27,7 @@ python3 -m dynamo.sglang \
--trust-remote-code \
--disaggregation-mode prefill \
--disaggregation-transfer-backend nixl \
--expert-distribution-recorder-mode stat \
--load-balance-method round_robin \
--port 30000 &
PREFILL_PID=$!

Expand All @@ -46,5 +42,5 @@ CUDA_VISIBLE_DEVICES=2,3 python3 -m dynamo.sglang \
--trust-remote-code \
--disaggregation-mode decode \
--disaggregation-transfer-backend nixl \
--expert-distribution-recorder-mode stat \
--prefill-round-robin-balance \
--port 31000
Loading