Update vLLM parameter max-seq-len-to-capture (#1809)

Signed-off-by: lvliang-intel <liang1.lv@intel.com>

DocSum/docker_compose/intel/hpu/gaudi/compose.yaml

@@ -28,7 +28,7 @@ services:
     cap_add:
       - SYS_NICE
     ipc: host
-    command: --model $LLM_MODEL_ID --tensor-parallel-size ${NUM_CARDS} --host 0.0.0.0 --port 80 --block-size ${BLOCK_SIZE} --max-num-seqs ${MAX_NUM_SEQS} --max-seq_len-to-capture ${MAX_SEQ_LEN_TO_CAPTURE}
+    command: --model $LLM_MODEL_ID --tensor-parallel-size ${NUM_CARDS} --host 0.0.0.0 --port 80 --block-size ${BLOCK_SIZE} --max-num-seqs ${MAX_NUM_SEQS} --max-seq-len-to-capture ${MAX_SEQ_LEN_TO_CAPTURE}
 
   llm-docsum-vllm:
     image: ${REGISTRY:-opea}/llm-docsum:${TAG:-latest}

DocSum/kubernetes/helm/gaudi-values.yaml

@@ -28,5 +28,5 @@ vllm:
     "--tensor-parallel-size", "1",
     "--block-size", "128",
     "--max-num-seqs", "256",
-    "--max-seq_len-to-capture", "2048"
+    "--max-seq-len-to-capture", "2048"
   ]