Quantong Qiu 359df6a7b6 refactor(paths): derive repository files from root

2026-07-20 17:33:51 +08:00

..

adaptive_config.env

fix(bench): use default limits and back off after OOM

2026-07-20 11:48:10 +08:00

compare.py

update 8k and 32k

2026-07-17 16:47:25 +08:00

config.env

refactor(paths): derive repository files from root

2026-07-20 17:33:51 +08:00

generate_scenarios.py

Reorganize experiments into hardware-specific subdirectories

2026-07-16 04:11:07 +00:00

matrix.json

update 8k and 32k

2026-07-17 16:47:25 +08:00

run_adaptive_concurrency_add16.sh

fix(sglang): cap SM120 CUDA graph prefill

2026-07-20 16:06:09 +08:00

run_adaptive_concurrency.sh

fix(sglang): cap SM120 CUDA graph prefill

2026-07-20 16:06:09 +08:00

run_bench.sh

fix(bench): use default limits and back off after OOM

2026-07-20 11:48:10 +08:00

run_sglang_in_container.sh

fix(bench): use default limits and back off after OOM

2026-07-20 11:48:10 +08:00

start_sglang_container.sh

update 8k and 32k

2026-07-17 16:47:25 +08:00

start_sglang_docker.sh

fix(sglang): cap SM120 CUDA graph prefill

2026-07-20 16:06:09 +08:00

start_sglang_dp.sh

fix(sglang): cap SM120 CUDA graph prefill

2026-07-20 16:06:09 +08:00