Zhiyi Hong 6d3338244b fix: cuda-graph-max-bs=64 (256 OOMs during capture)

2026-07-28 17:31:52 +08:00

..

config.env

fix: cuda-graph-max-bs=64 (256 OOMs during capture)

2026-07-28 17:31:52 +08:00

run_batch.sh

add tp = 16 deepseek v4 pro sglang bench

2026-07-28 17:09:26 +08:00

start_and_bench.sh

add tp = 16 deepseek v4 pro sglang bench

2026-07-28 17:09:26 +08:00

start_sglang_multinode.sh

add tp = 16 deepseek v4 pro sglang bench

2026-07-28 17:09:26 +08:00

stop_sglang_multinode.sh

add tp = 16 deepseek v4 pro sglang bench

2026-07-28 17:09:26 +08:00