Support Kimi Linear (#12469)

Co-authored-by: yizhang2077 <1109276519@qq.com>
2025-11-01 05:03:35 +08:00
parent 30ad107028
commit a4bf5c6ad2
18 changed files with 2847 additions and 112 deletions
--- a/python/sglang/srt/server_args.py
+++ b/python/sglang/srt/server_args.py
@@ -1028,6 +1028,11 @@ class ServerArgs:
            logger.info(
                f"Using {self.attention_backend} as attention backend for {model_arch}."
            )
+        elif model_arch in ["KimiLinearForCausalLM"]:
+            logger.warning(
+                f"Disabling Radix Cache for {model_arch} as it is not yet supported."
+            )
+            self.disable_radix_cache = True

        if is_deepseek_nsa(hf_config):
            if (