Update README.md

README.md

@@ -46,7 +46,10 @@ The following table presents representative benchmarks for Ling-3.0-tiny:
 
 # Quickstart
 ## SGLang
-The hardware- and recipe-specific launch matrix (BF16/FP8 × Low-Latency / High-Throughput / HiCache + Mooncake) includes a live command generator and verified configurations:
+The hardware- and recipe-specific launch matrix (BF16/FP8 × Low-Latency / High-Throughput / HiCache + Mooncake), with a live command generator and verified configurations, lives in the SGLang cookbook:
+
+**Cookbook:** https://docs.sglang.io/cookbook/autoregressive/InclusionAI/Ling-3.0-tiny
+
 
 ### Install SGLang
 Use the pre-built image that tracks the Ling-3.0 runtime:
@@ -56,7 +59,7 @@ docker pull lmsysorg/sglang:dev-Ling-3.0-tiny
 ```
 
 ### Run Inference
-We recommend the low-latency recipe (built-in MTP / NEXTN, 256K YaRN context) on 1× 141GB-class GPU (H20-3e) or a 1-GPU Blackwell node:
+Recommended low-latency recipe (built-in MTP / NEXTN, 256K YaRN context) on 1× 141GB-class GPU (H20-3e) or a 1-GPU Blackwell node:
 
 **Server**
 
@@ -79,7 +82,7 @@ docker run --rm --gpus all --ipc=host --shm-size 32g \
 
 **Client**
 
-The chat template and the `ling3` reasoning parser enable thinking mode by default. To disable it for an individual request, set `"chat_template_kwargs": {"enable_thinking": false}`. We recommend the sampling parameters `temperature=1.0`, `top_p=0.95`, and `top_k=20`.
+Thinking is enabled by default by both the chat template and the `ling3` reasoning parser. Disable it per request with `"chat_template_kwargs": {"enable_thinking": false}`. We recommend the sampling parameters `temperature=1.0`, `top_p=0.95`, and `top_k=20`.
 
 ```bash
 curl -s http://localhost:30000/v1/chat/completions \
@@ -92,6 +95,7 @@ curl -s http://localhost:30000/v1/chat/completions \
        "top_p": 0.95
      }'
 ```
+For `--reasoning-parser ling3` / `--tool-call-parser ling3`, the HiCache + Mooncake L3 setup, and GSM8K / bench_serving reproduction commands, see the cookbook page linked above.
 
 ## vLLM
 ### Install our vLLM
@@ -110,7 +114,7 @@ VLLM_USE_PRECOMPILED=1 uv pip install --editable . --torch-backend=auto
 ```
 
 ### Run Inference
-The following example runs Ling-3.0-tiny on 1 GPU, with the server listening on port `${PORT}`:
+Here is the example to run Ling-3.0-tiny with 1 GPU, where the server port is `${PORT}`:
 
 **Server**
 
@@ -166,11 +170,11 @@ cmake --build build --parallel 8
 >
 
 ### Import Model
-Replace `/absolute/path/to/fp8_weights` with the absolute path to the FP8 model weights directory. The imported model will be named `ling-tiny-fp8`:
+Replace `/absolute/path/to/bf16_weights` with the absolute path to the BF16 model weights directory. The imported model will be named `ling-tiny-bf16`:
 
 ```bash
-printf 'FROM /absolute/path/to/fp8_weights\n' > /tmp/Modelfile.ling
-./ollama create ling-tiny-fp8 --experimental -f /tmp/Modelfile.ling
+printf 'FROM /absolute/path/to/bf16_weights\n' > /tmp/Modelfile.ling
+./ollama create ling-tiny-bf16 --experimental -f /tmp/Modelfile.ling
 ```
 
 ### Start Service
@@ -184,7 +188,7 @@ OLLAMA_CONTEXT_LENGTH=8192 ./ollama serve
 ### Call API
 ```bash
 curl -sS http://127.0.0.1:11434/api/generate -d '{
-  "model": "ling-tiny-fp8",
+  "model": "ling-tiny-bf16",
   "prompt": "<role>SYSTEM</role>detailed thinking on<|role_end|><role>HUMAN</role>Calculate 17 × 23 and output only the number.<|role_end|><role>ASSISTANT</role>\n<think>",
   "raw": true,
   "think": true,