fix: Remove debug logging from aiperf benchmarking (#5010)

benchmarks/llm/perf.sh

@@ -236,7 +236,6 @@ for concurrency in "${concurrency_array[@]}"; do
     --random-seed 100 \
     --artifact-dir ${artifact_dir} \
     --ui simple \
-    -v \
     -H 'Authorization: Bearer NOT USED' \
     -H 'Accept: text/event-stream'
 

docs/backends/trtllm/gpt-oss.md

@@ -430,7 +430,6 @@ aiperf profile \
     --num-dataset-entries 8000 \
     --random-seed 100 \
     --artifact-dir /tmp/benchmark-results \
-    -v \
     -H 'Authorization: Bearer NOT USED' \
     -H 'Accept: text/event-stream'
 ```

examples/backends/trtllm/performance_sweeps/scripts/bench.sh

@@ -174,7 +174,6 @@ for concurrency in ${concurrency_list}; do
 	    --num-dataset-entries ${num_prompts} \
     	--random-seed 100 \
     	--artifact-dir ${artifacts_dir} \
-    	-v \
     	-H 'Authorization: Bearer NOT USED' \
     	-H 'Accept: text/event-stream'
     echo "Benchmark with concurrency ${concurrency} done"

examples/deployments/router_standalone/perf.sh

@@ -47,6 +47,5 @@ aiperf profile \
   --request-count ${num_requests} \
   --num-dataset-entries ${num_unique_prompts} \
   --random-seed ${seed} \
-  -v \
   -H 'Authorization: Bearer NOT USED' \
   -H 'Accept: text/event-stream'

tests/planner/README.md

@@ -286,8 +286,7 @@ aiperf profile \
   --streaming \
   --input-file /workspace/rr-5-45_i3000o300.jsonl \ # path to the generated load dataset \
   --custom-dataset-type mooncake_trace \
-  --goodput "time_to_first_token:200 inter_token_latency:10" \
-  -v
+  --goodput "time_to_first_token:200 inter_token_latency:10"
 ```
 
 > [!NOTE]