[Feature] Initial support for multi-LoRA serving (#1307)

python/sglang/srt/server.py

@@ -611,6 +611,7 @@ class Runtime:
         return_logprob: Optional[Union[List[bool], bool]] = False,
         logprob_start_len: Optional[Union[List[int], int]] = None,
         top_logprobs_num: Optional[Union[List[int], int]] = None,
+        lora_path: Optional[List[Optional[str]]] = None,
     ):
         json_data = {
             "text": prompt,
@@ -618,7 +619,9 @@ class Runtime:
             "return_logprob": return_logprob,
             "logprob_start_len": logprob_start_len,
             "top_logprobs_num": top_logprobs_num,
+            "lora_path": lora_path,
         }
+        assert not isinstance(lora_path, list) or len(lora_path) == len(prompt)
         response = requests.post(
             self.url + "/generate",
             json=json_data,