Update SGLang quickstart to the day-0 image and cookbook

README.md

@@ -45,60 +45,45 @@ We also introduce **LingCode**, a harness built on the open-source coding agent
 
 ## Quickstart
 #### SGLang (Recommended)
-**Install our SGLang**
 
-```bash
-pip install uv
+The day-0 SGLang image includes Ling-3.1-flash support, MTP (NEXTN) speculative decoding, and the Hopper decode optimizations:
 
-uv venv ~/my_ling_env
-
-source ~/my_ling_env/bin/activate
-
-git clone -b ling-v3-open https://github.com/inclusionAI/sglang_ling_v3.git
-cd sglang_ling_v3
-
-pip install --upgrade pip
-pip install -e "python"
+```bash
+docker pull lmsysorg/sglang:dev-ling-3.1-flash
 ```
 
 ##### Run Inference
-Both FP8 and mxfp4 models are supported by SGLang now. It depends on the dtype of the model in `${MODEL_PATH}`. Here is the example to run Ling-3.1-flash with 8 GPUs, where the master node IP is `${MASTER_IP}` and server port is `${PORT}`:
 
-**Server**
-
-**1. Standard Inference**
+**Server** (8x H200, TP8 + EP8):
 
 ```bash
-sglang serve \
-  --model-path $MODEL_PATH \
-  --port $PORT \
-  --trust-remote-code \
-  --tp 8 \
-  --enable-cache-report \
-  --log-level info \
-  --enable-metrics \
-  --mem-fraction-static 0.85 \
-  --max-running-requests 64 \
-  --chunked-prefill-size 8192 \
-  --speculative-algorithm NEXTN \
-  --allow-auto-truncate \
-  --tool-call-parser ling3 \
-  --reasoning-parser ling3
+docker run --gpus all --network host --ipc=host --rm \
+  lmsysorg/sglang:dev-ling-3.1-flash \
+  python3 -m sglang.launch_server \
+    --model-path inclusionAI/Ling-3.1-flash \
+    --tp 8 --ep 8 \
+    --speculative-algorithm NEXTN \
+    --host 0.0.0.0 --port 30000
 ```
 
+On 4x GB300, use `--tp 4 --ep 4` instead. Hopper decode optimizations (optional, ~10% faster batch-1 decode) can be enabled with `SGLANG_ENABLE_FP8_BLOCK_GEMV=1` and `SGLANG_ENABLE_FUSED_KDA_OUTPUT_QUANT=1`.
+
 **Client**
 
 ```bash
-curl -s http://${MASTER_IP}:${PORT}/v1/chat/completions \
+curl -s http://localhost:30000/v1/chat/completions \
   -H "Content-Type: application/json" \
-  -d '{"model": "auto", 
-       "messages": [{"role": "user", "content": "What is the capital of France?"}],       "chat_template_kwargs": {"enable_thinking": true},
+  -d '{"model": "Ling-3.1-flash",
+       "messages": [{"role": "user", "content": "What is the capital of France?"}],
+       "chat_template_kwargs": {"enable_thinking": true},
        "stream": true,
-       "temperature": 1.0, 
+       "temperature": 1.0,
        "top_k": 20,
        "top_p": 0.95}'
 ```
 
+Verified recipes for H200, GB300, H800, H100, and B200, plus HiCache (Mooncake L3), reasoning on/off, tool calling, and measured accuracy/speed numbers, are in the [SGLang Ling-3.1-flash cookbook](https://docs.sglang.io/cookbook/autoregressive/InclusionAI/Ling-3.1-flash).
+
 #### vLLM
 ##### Environment Preparation
 ```bash