History

yy-fighting 1482601ae5 Add num_prompts = 5×concurrency convention and update all experiments

- Document the rule in docs/EXPERIMENT_GUIDE.md section 7
- Update all config.env SCENARIOS to follow the 5x rule
- Migrate dsv4_h200_sglang, dsv4_h200_vllm, dsv4_p800_sglang
  from global NUM_PROMPTS to per-scenario num_prompts
- Keep long-context phase2 as exception (low counts documented)
- Add legacy 3-field fallback in run_bench.sh loops

2026-07-09 09:26:41 +00:00

results/20260708-062348

fix(dsv4_h200_vllm): scenario array parsing and sglang output format

2026-07-08 06:31:03 +00:00

config.env

Add num_prompts = 5×concurrency convention and update all experiments

2026-07-09 09:26:41 +00:00

parse_results.py

fix(dsv4_h200_vllm): scenario array parsing and sglang output format

2026-07-08 06:31:03 +00:00

README.md

refactor: relocate old docs and add dsv4_h200_vllm experiment

2026-07-08 06:19:40 +00:00

run_bench.sh

Add num_prompts = 5×concurrency convention and update all experiments

2026-07-09 09:26:41 +00:00

start_server.sh

refactor: relocate old docs and add dsv4_h200_vllm experiment

2026-07-08 06:19:40 +00:00

README.md

DSV4 H200 vLLM Baseline Benchmark

NVIDIA H200 + native vllm + DeepSeek-V4-Flash baseline benchmark experiment.

This experiment uses:

/data/user1/yy/envs/vllm as the server environment
/data/user1/yy/envs/sglang as the benchmark client environment

Quick Start

# Run the full experiment (start server + benchmark + parse)
bash experiments/dsv4_h200_vllm/run_bench.sh

# Reuse an already-running server
SKIP_MANAGE_SERVER=1 bash experiments/dsv4_h200_vllm/run_bench.sh

Results land in experiments/dsv4_h200_vllm/results/<RUN_ID>/.

Configuration

Edit config.env or override via environment variables:

MODEL_PATH=/data/models/DeepSeek-V4-Flash \
PORT=30005 \
SCENARIOS="32 512 256   128 512 256" \
bash experiments/dsv4_h200_vllm/run_bench.sh

Files

File	Purpose
`config.env`	Experiment-level configuration (model, port, venv paths, scenarios)
`start_server.sh`	Start a plain vLLM baseline server for DeepSeek-V4-Flash
`run_bench.sh`	Orchestrator: metadata → server → benchmark → parse
`parse_results.py`	Parse raw JSONL outputs into `results.json` + `report.md`

Platform

This experiment targets platforms/nvidia_h200.env.