- Add experiments/dsv4_h200_sglang (config, server start, orchestrator, parser, README) - Fix start_server.sh to wait for HTTP 200 via curl --fail instead of treating 503 as ready - Add H200 SGLang baseline to root README and update .gitignore for per-run raw_outputs/logs - Remove stale experiments/dsv4_h200_dspark/DSPARK_FIX_PR_PREP.md
DSV4 H200 DSpark Benchmark
NVIDIA H200 + native vllm-dspark + DeepSeek-V4-Flash-DSpark benchmark experiment.
This is a migration wrapper: it reuses the proven legacy scripts under
scripts/benchmark_dspark_0707/ and scripts/start_dsv4_dspark_8card.sh,
but stores results in the new experiments/<name>/results/<RUN_ID>/ layout.
Quick Start
# Run the full DSpark P1/P2/P3 grid
bash experiments/dsv4_h200_dspark/run_bench.sh
# Reuse an already-running server
SKIP_MANAGE_SERVER=1 bash experiments/dsv4_h200_dspark/run_bench.sh
Results land in experiments/dsv4_h200_dspark/results/<RUN_ID>/.
Configuration
Edit config.env or override via environment variables:
MODEL_PATH=/data/models/DeepSeek-V4-Flash-DSpark \
PORT=30004 \
bash experiments/dsv4_h200_dspark/run_bench.sh
Files
| File | Purpose |
|---|---|
config.env |
Experiment-level configuration (model, port, venv paths) |
run_bench.sh |
Orchestrator: metadata → legacy grid benchmark → parse |
parse_results.py |
Wraps the legacy parser to generate report.md |
Platform
This experiment targets platforms/nvidia_h200.env.