diff --git a/start.sh b/start.sh
index d1eaf80..0cb179b 100755
--- a/start.sh
+++ b/start.sh
@@ -258,18 +258,19 @@ exec ${topo_launch_prefix:+$topo_launch_prefix} "$VENV/bin/vllm" serve "$CKPT" \
   --host "${HOST:-127.0.0.1}" --port "${PORT:-8000}" \
   --tensor-parallel-size 2 --pipeline-parallel-size 2 --enable-expert-parallel \
   --speculative-config '{"method":"mtp","num_speculative_tokens":3,"draft_sample_method":"probabilistic"}' \
-  --max-model-len 262144 --max-num-seqs 2 --max-num-batched-tokens 4096 \
+  --max-model-len 262144 --max-num-seqs 4 --max-num-batched-tokens 2048 \
   --gpu-memory-utilization 0.96 --kv-cache-memory 4100000000 --kv-cache-dtype fp8_e4m3 \
   --limit-mm-per-prompt '{"image":42,"video":0}' --mm-processor-cache-gb 0 \
   --mm-processor-kwargs '{"size":{"longest_edge":4194304,"shortest_edge":65536}}' \
-  --compilation-config '{"cudagraph_mode":"FULL_AND_PIECEWISE","cudagraph_capture_sizes":[1,2,3,4,6,8,12,16,24,32]}' \
+  --compilation-config '{"cudagraph_mode":"FULL_AND_PIECEWISE","cudagraph_capture_sizes":[1,2,4,8,12,16]}' \
   --enable-prefix-caching --enable-prompt-tokens-details \
   --no-enable-flashinfer-autotune \
   --enable-auto-tool-choice --tool-call-parser qwen3_coder --reasoning-parser qwen3 \
   --override-generation-config '{"temperature": 1.0, "top_p": 0.95, "top_k": 20, "min_p": 0.0, "presence_penalty": 0.0, "repetition_penalty": 1.0}' \
-  --default-chat-template-kwargs '{"enable_thinking": true, "reasoning_effort": "low"}' \
+  --default-chat-template-kwargs '{"enable_thinking": true, "reasoning_effort": "xhigh"}' \
   --shutdown-timeout 10 \
-  --block-size 4096 --use-replayssm \
+  --block-size 2048 --use-replayssm \
   --prefix-match-unit 64 \
   --safetensors-load-strategy prefetch \
+  --disable-uvicorn-access-log \
   "$@"