Root User 5e95cee1a0 bench: add adaptive concurrency search

2026-07-11 06:11:40 +00:00

..

results/20260709-152419_matrix

vllm tp_dp_matrix: add final results (report, results.json, comparison, scenarios)

2026-07-10 02:20:36 +00:00

adaptive_config.env

bench: add adaptive concurrency search

2026-07-11 06:11:40 +00:00

compare.py

vllm tp_dp_matrix: dockerize deployment and fix missing DOCKER_CLIENT_IMAGE export

2026-07-11 06:11:40 +00:00

config.env

bench: add adaptive concurrency search

2026-07-11 06:11:40 +00:00

generate_scenarios.py

vllm tp_dp_matrix: dockerize deployment and fix missing DOCKER_CLIENT_IMAGE export

2026-07-11 06:11:40 +00:00

matrix.json

dsv4_h200_vllm_tp_dp_matrix: single server per config, OOM/restart handling, DRY_RUN/GRID_LIMIT, include 1M

2026-07-09 10:50:59 +00:00

README_adaptive_concurrency.md

bench: add adaptive concurrency search

2026-07-11 06:11:40 +00:00

run_adaptive_concurrency.sh

bench: add adaptive concurrency search

2026-07-11 06:11:40 +00:00

run_bench.sh

vllm tp_dp_matrix: dockerize deployment and fix missing DOCKER_CLIENT_IMAGE export

2026-07-11 06:11:40 +00:00

smoke_matrix.json

add dsv4_h200_vllm_tp_dp_matrix experiment (TP×DP matrix with Y-only mode, 1M excluded)

2026-07-09 09:55:18 +00:00

start_vllm_docker.sh

vllm tp_dp_matrix: dockerize deployment and fix missing DOCKER_CLIENT_IMAGE export

2026-07-11 06:11:40 +00:00

start_vllm_dp.sh

vllm tp_dp_matrix: dockerize deployment and fix missing DOCKER_CLIENT_IMAGE export

2026-07-11 06:11:40 +00:00