Remove deprecated arg in vllm serve command (#1230)

dennisYehCienet · web-flow · commit a4cc292a998f · 2025-12-02T20:14:44.000-08:00
Signed-off-by: dennis yeh &lt;dennis.yeh@cienet.com&gt;
diff --git a/tests/e2e/benchmarking/mm_bench_recipe.sh b/tests/e2e/benchmarking/mm_bench_recipe.sh
@@ -78,7 +78,7 @@ checkThroughput() {
 }
 
 echo "Spinning up the vLLM server..."
-(vllm serve "$model_name" --tensor-parallel-size 1 --pipeline-parallel-size 1 --dtype bfloat16 --gpu-memory-utilization 0.98 --max-model-len "$max_model_len" --limit-mm-per-prompt '{"image": 10, "video": 0}' --mm-processor-kwargs '{"max_pixels": 1003520}' --guided-decoding-backend "xgrammar" --disable-chunked-mm-input  2>&1 | tee -a "$LOG_FILE") &
+(vllm serve "$model_name" --tensor-parallel-size 1 --pipeline-parallel-size 1 --dtype bfloat16 --gpu-memory-utilization 0.98 --max-model-len "$max_model_len" --limit-mm-per-prompt '{"image": 10, "video": 0}' --mm-processor-kwargs '{"max_pixels": 1003520}' --disable-chunked-mm-input  2>&1 | tee -a "$LOG_FILE") &
 
 
 # Run a busy loop to block until the server is ready to receive requests

Original file line number	Diff line number	Diff line change
`@@ -78,7 +78,7 @@ checkThroughput() {`
`78`	`78`	`}`
`79`	`79`
`80`	`80`	`echo "Spinning up the vLLM server..."`
`81`		`-(vllm serve "$model_name" --tensor-parallel-size 1 --pipeline-parallel-size 1 --dtype bfloat16 --gpu-memory-utilization 0.98 --max-model-len "$max_model_len" --limit-mm-per-prompt '{"image": 10, "video": 0}' --mm-processor-kwargs '{"max_pixels": 1003520}' --guided-decoding-backend "xgrammar" --disable-chunked-mm-input 2>&1 \| tee -a "$LOG_FILE") &`
	`81`	`+(vllm serve "$model_name" --tensor-parallel-size 1 --pipeline-parallel-size 1 --dtype bfloat16 --gpu-memory-utilization 0.98 --max-model-len "$max_model_len" --limit-mm-per-prompt '{"image": 10, "video": 0}' --mm-processor-kwargs '{"max_pixels": 1003520}' --disable-chunked-mm-input 2>&1 \| tee -a "$LOG_FILE") &`
`82`	`82`
`83`	`83`
`84`	`84`	`# Run a busy loop to block until the server is ready to receive requests`