[FDConfig]Turn on the CUDAGraph + RL switch (#4508)

* Turn on the CUDAGraph + RL switch

* reduce max_num_seqs and number of request

tests/ce/stable_cases/launch_model.sh

@@ -38,7 +38,7 @@ python -m fastdeploy.entrypoints.openai.api_server \
        --cache-queue-port ${FD_CACHE_QUEUE_PORT} \
        --quantization wint8 \
        --max-model-len 32768 \
-       --max-num-seqs 256 \
+       --max-num-seqs 1 \
        --gpu-memory-utilization 0.9 \
        --model "$MODEL_PATH" \
        --load-strategy ipc_snapshot \

tests/ce/stable_cases/run.sh

@@ -12,7 +12,7 @@ PORT="${FD_API_PORT}"  # 这里需要配合启动脚本那个URL PORT
 BASE_URL="http://$HOST:$PORT"
 
 TOTAL_ROUNDS=30
-CHAT_REQUESTS_PER_ROUND=5
+CHAT_REQUESTS_PER_ROUND=1
 export CUDA_VISIBLE_DEVICES=0,1
 MAX_MEMORY_MB=10240  # 10GB