2 Commits

Author SHA1 Message Date
Quantong Qiu
4d5b6a77ca Add custom benchmark setup for vLLM TP=8 on dsv4 H200
- Create configuration file for the custom benchmark experiment.
- Implement result parsing script to handle JSONL outputs from the benchmark.
- Develop run script to orchestrate the benchmark execution, including server management and health checks.
- Add server start script to launch a single vLLM service on all available GPUs.
2026-07-10 09:40:10 +00:00
Quantong Qiu
db00c1b1ac Add custom benchmark setup for vLLM TP=2 on dsv4_h200
- Create configuration file for dsv4_h200_vllm_tp2_custom_bench.
- Implement result parsing script to handle JSONL outputs from bench_client.py.
- Develop run_bench.sh script to orchestrate multi-service vLLM benchmarking.
- Add start_server.sh script to launch independent vLLM services on specified GPU pairs.
2026-07-10 09:06:10 +00:00