We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
1 parent 905589a commit fd77c45Copy full SHA for fd77c45
1 file changed
benchmarks/gptoss_fp4_h100_docker.sh
@@ -51,7 +51,7 @@ python3 $BENCH_SERVING_DIR/benchmark_serving.py \
51
--base-url=http://localhost:$PORT \
52
--dataset-name=random \
53
--random-input-len=$ISL --random-output-len=$OSL --random-range-ratio=$RANDOM_RANGE_RATIO \
54
---num-prompts=$(( $CONC * 10 )) --max-concurrency=$CONC \
+--num-prompts=$(( $CONC * 10 )) --max-concurrency=512 \
55
--request-rate=inf --ignore-eos \
56
--save-result --percentile-metrics='ttft,tpot,itl,e2el' \
57
--result-dir=/workspace/ \
0 commit comments