model: support intern-s1 (#8350)

Signed-off-by: Xinyuan Tong <xinyuantong.cs@gmail.com>
Co-authored-by: zxy <zhou0493@e.ntu.edu.sg>
Co-authored-by: Xinyuan Tong <xinyuantong.cs@gmail.com>
Co-authored-by: Mick <mickjagger19@icloud.com>
Co-authored-by: Xinyuan Tong <115166877+JustinTong0323@users.noreply.github.com>

python/sglang/srt/configs/internvl.py

@@ -10,6 +10,7 @@ from transformers import (
     PretrainedConfig,
     PreTrainedTokenizer,
     Qwen2Config,
+    Qwen3Config,
 )
 
 from sglang.utils import logger
@@ -314,6 +315,8 @@ class InternVLChatConfig(PretrainedConfig):
             self.llm_config = InternLM2Config(**llm_config)
         elif llm_config.get("architectures")[0] == "Qwen2ForCausalLM":
             self.llm_config = Qwen2Config(**llm_config)
+        elif llm_config.get("architectures")[0] == "Qwen3MoeForCausalLM":
+            self.llm_config = Qwen3Config(**llm_config)
         else:
             raise ValueError(
                 "Unsupported architecture: {}".format(

python/sglang/srt/configs/model_config.py

@@ -635,6 +635,7 @@ multimodal_model_archs = [
     "Qwen2_5_VLForConditionalGeneration",
     "KimiVLForConditionalGeneration",
     "InternVLChatModel",
+    "InternS1ForConditionalGeneration",
     "Phi4MMForCausalLM",
     "VILAForConditionalGeneration",
 ]