fix large completion probe timeout

worklogs/remote_scripts/start_platform_245k_repro.sh

@@ -4,6 +4,8 @@ set -euo pipefail
 OUT="${1:-/root/work/logs/platform_245k_repro_20260715_01}"
 PORT="${PORT:-1111}"
 MODEL="${MODEL:-/root/public-storage/models/Qwen/Qwen3.6-35B-A3B}"
+MAX_MODEL_LEN="${MAX_MODEL_LEN:-245000}"
+MAX_SEQ_LEN_TO_CAPTURE="${MAX_SEQ_LEN_TO_CAPTURE:-32768}"
 MAX_NUM_BATCHED_TOKENS="${MAX_NUM_BATCHED_TOKENS:-16384}"
 MOE_DECODE_NATIVE="${MOE_DECODE_NATIVE:-0}"
 mkdir -p "$OUT"
@@ -57,7 +59,7 @@ print("sigkill_pids", left)
 PY
 
 echo "[repro] gpu before start" | tee "$OUT/driver.log"
-echo "[repro] MAX_NUM_BATCHED_TOKENS=$MAX_NUM_BATCHED_TOKENS MOE_DECODE_NATIVE=$MOE_DECODE_NATIVE" | tee -a "$OUT/driver.log"
+echo "[repro] MAX_MODEL_LEN=$MAX_MODEL_LEN MAX_SEQ_LEN_TO_CAPTURE=$MAX_SEQ_LEN_TO_CAPTURE MAX_NUM_BATCHED_TOKENS=$MAX_NUM_BATCHED_TOKENS MOE_DECODE_NATIVE=$MOE_DECODE_NATIVE" | tee -a "$OUT/driver.log"
 LD_LIBRARY_PATH=/usr/local/corex-3.2.3/lib64:/usr/local/corex/lib64:/usr/local/corex/lib:/usr/local/iluvatar/lib64 \
   /usr/local/corex/bin/ixsmi | tee -a "$OUT/driver.log"
 
@@ -66,7 +68,7 @@ nohup python3 -m vllm.entrypoints.openai.api_server \
   --served-model-name llm \
   --host 0.0.0.0 \
   --port "$PORT" \
-  --max-model-len 245000 \
+  --max-model-len "$MAX_MODEL_LEN" \
   --enforce-eager \
   --gpu-memory-utilization 0.9 \
   --trust-remote-code \
@@ -76,7 +78,7 @@ nohup python3 -m vllm.entrypoints.openai.api_server \
   --disable-frontend-multiprocessing \
   --max-num-batched-tokens "$MAX_NUM_BATCHED_TOKENS" \
   --enable-chunked-prefill \
-  --max-seq-len-to-capture 245000 \
+  --max-seq-len-to-capture "$MAX_SEQ_LEN_TO_CAPTURE" \
   --enable-auto-tool-choice \
   --tool-call-parser qwen3_coder \
   --reasoning-parser qwen3 \