Add SGLang serving recipe to README

README.md

@@ -152,7 +152,6 @@ cd sglang
 pip install -e "python[all]"
 
 sglang serve \
-    --trust-remote-code \
     --model-path poolside/Laguna-M.1 \
     --tool-call-parser poolside_v1 \
     --reasoning-parser poolside_v1 \
@@ -160,7 +159,7 @@ sglang serve \
     --host 0.0.0.0
 ```
 
-Quantized Laguna M.1 checkpoints are also available as [Laguna-M.1-FP8](https://huggingface.co/poolside/Laguna-M.1-FP8) and [Laguna-M.1-NVFP4](https://huggingface.co/poolside/Laguna-M.1-NVFP4). SGLang reads the checkpoint `quantization_config`, so you can use the same launch command after replacing the model ID. For more SGLang-specific deployment details, see the [SGLang Cookbook](https://docs.sglang.io/cookbook/autoregressive/Poolside/Laguna-M.1).
+Quantized Laguna M.1 checkpoints are also available as [Laguna-M.1-FP8](https://huggingface.co/poolside/Laguna-M.1-FP8) and [Laguna-M.1-NVFP4](https://huggingface.co/poolside/Laguna-M.1-NVFP4). SGLang reads the checkpoint `quantization_config`, so you can use the same launch command after replacing the model ID. For more SGLang-specific deployment details, see the [SGLang Cookbook](https://docs.sglang.io/cookbook/autoregressive/Poolside/Laguna-XS.2) which uses the same Laguna implementation path.
 
 #### Transformers
 

generation_config.json

@@ -9,10 +9,5 @@
   "pad_token_id": 9,
   "temperature": 1.0,
   "top_p": 1.0,
-  "min_p": 0.0,
-  "tool_call_parser": "poolside_v1",
-  "reasoning_parser": "poolside_v1",
-  "default_chat_template_kwargs": {
-    "enable_thinking": true
-  }
-}
+  "min_p": 0.0
+}

tokenizer_config.json

@@ -571,5 +571,6 @@
   "pad_token": "〈|PAD|〉",
   "sep_token": "〈|SEP|〉",
   "tokenizer_class": "PreTrainedTokenizerFast",
-  "unk_token": "〈|UNK|〉"
-}
+  "unk_token": "〈|UNK|〉",
+  "chat_template": "{% include 'chat_template.jinja' %}"
+}