Skip to content

Update readme for multi-gpu config #8

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
TerrenceZhangX merged 2 commits into from
Jan 13, 2026
Merged

Update readme for multi-gpu config #8

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
3704bda
Update readme for multi-gpu setting
Jan 13, 2026
bec0d2b
Add timeout config and update tp/ep size
Jan 13, 2026
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
12 changes: 8 additions & 4 deletions README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -61,24 +61,28 @@ mkdir -p /data/flowsim-simulate
#### Step 1: Profile (Generate Traces)

```bash
sudo docker run --rm --gpus=all \
sudo docker run --gpus=all \
-v /data/flowsim-profile:/workspace/profile \
-v /data/flowsim-simulate:/workspace/simulate \
-w /flowsim \
--cap-add=SYS_ADMIN \
--network=host \
--shm-size 911G \
flowsim-image \
python scripts/run_profile.py \
--profile-dir /workspace/profile \
--log-dir /workspace/profile/logs \
--server-opts "--model-path /flowsim/workload/models/configs/deepseek/ --load-format dummy --tp 1 --host 0.0.0.0 --port 30001 --attention-backend flashinfer --disable-cuda-graph" \
--bench-opts "--backend sglang --host 0.0.0.0 --port 30001 --dataset-name defined-len --prefill-decode-lens 32768:8 --num-prompts 16 --profile"
--bench-timeout 3600 \
--server-opts "--model-path /flowsim/workload/models/configs/deepseek/ --load-format dummy --tp 4 --ep 4 --host 0.0.0.0 --port 30001 --attention-backend flashinfer --disable-cuda-graph" \
--bench-opts "--backend sglang --host 0.0.0.0 --port 30001 --dataset-name defined-len --prefill-decode-lens 1024:8 --num-prompts 1 --profile"
```

**What this does:**
- Starts an sglang server with profiling enabled
- Runs benchmark requests against it
- Generates `*.trace.json.gz` files in `/data/flowsim-profile` (mounted as `/workspace/profile`)

**Note:** The first run will be slow (~10 minutes) due to DeepGEMM kernel warmup and compilation. For stable performance, avoid using `--rm` flag and reuse the same container. Subsequent runs with similar configurations will be faster.
**Note:** The first run will be slow (~10 minutes) due to DeepGEMM kernel warmup and compilation. For stable performance, avoid using `--rm` flag and reuse the same container using `sudo docker exec -it <container_id> bash`. Subsequent runs with similar configurations will be faster.

**Tip:**
- Adjust `--server-opts` and `--bench-opts` to match your model, parallelism (TP/DP/EP), and workload requirements. All `sglang.launch_server` and `bench_serving.py` parameters are supported.
Expand Down
Loading