Skip to content

Commit fd77c45

Browse files
committed
reverting max conc to 512 on gptoss fp4 b200 docker
1 parent 905589a commit fd77c45

1 file changed

Lines changed: 1 addition & 1 deletion

File tree

benchmarks/gptoss_fp4_h100_docker.sh

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -51,7 +51,7 @@ python3 $BENCH_SERVING_DIR/benchmark_serving.py \
5151
--base-url=http://localhost:$PORT \
5252
--dataset-name=random \
5353
--random-input-len=$ISL --random-output-len=$OSL --random-range-ratio=$RANDOM_RANGE_RATIO \
54-
--num-prompts=$(( $CONC * 10 )) --max-concurrency=$CONC \
54+
--num-prompts=$(( $CONC * 10 )) --max-concurrency=512 \
5555
--request-rate=inf --ignore-eos \
5656
--save-result --percentile-metrics='ttft,tpot,itl,e2el' \
5757
--result-dir=/workspace/ \

0 commit comments

Comments
 (0)