[Docs] clean up structured outputs docs (#2654)

python/sglang/srt/openai_api/protocol.py

@@ -171,15 +171,15 @@ class CompletionRequest(BaseModel):
     top_k: int = -1
     min_p: float = 0.0
     min_tokens: int = 0
-    regex: Optional[str] = None
     json_schema: Optional[str] = None
+    regex: Optional[str] = None
+    ebnf: Optional[str] = None
     repetition_penalty: float = 1.0
     stop_token_ids: Optional[List[int]] = None
     no_stop_trim: bool = False
     ignore_eos: bool = False
     skip_special_tokens: bool = True
     lora_path: Optional[Union[List[Optional[str]], Optional[str]]] = None
-    ebnf: Optional[str] = None
 
 
 class CompletionResponseChoice(BaseModel):
@@ -315,13 +315,13 @@ class ChatCompletionRequest(BaseModel):
     min_p: float = 0.0
     min_tokens: int = 0
     regex: Optional[str] = None
+    ebnf: Optional[str] = None
     repetition_penalty: float = 1.0
     stop_token_ids: Optional[List[int]] = None
     no_stop_trim: bool = False
     ignore_eos: bool = False
     skip_special_tokens: bool = True
     lora_path: Optional[Union[List[Optional[str]], Optional[str]]] = None
-    ebnf: Optional[str] = None
 
 
 class FunctionResponse(BaseModel):

python/sglang/srt/sampling/sampling_params.py

@@ -19,6 +19,14 @@ _SAMPLING_EPS = 1e-6
 
 
 class SamplingParams:
+    """
+    The sampling parameters.
+
+    See docs/references/sampling_params.md or
+    https://sgl-project.github.io/references/sampling_params.html
+    for the documentation.
+    """
+
     def __init__(
         self,
         max_new_tokens: int = 128,
@@ -33,9 +41,9 @@ class SamplingParams:
         repetition_penalty: float = 1.0,
         min_new_tokens: int = 0,
         spaces_between_special_tokens: bool = True,
-        regex: Optional[str] = None,
         n: int = 1,
         json_schema: Optional[str] = None,
+        regex: Optional[str] = None,
         ebnf: Optional[str] = None,
         no_stop_trim: bool = False,
         ignore_eos: bool = False,

python/sglang/srt/server.py

@@ -578,6 +578,8 @@ def _set_envs_and_config(server_args: ServerArgs):
     os.environ["NCCL_NVLS_ENABLE"] = "0"
     os.environ["TORCH_NCCL_AVOID_RECORD_STREAMS"] = "1"
     os.environ["CUDA_DEVICE_MAX_CONNECTIONS"] = "4"
+    if "GLOO_SOCKET_IFNAME" not in os.environ:
+        os.environ["GLOO_SOCKET_IFNAME"] = "eth0"
 
     # Set prometheus env vars
     if server_args.enable_metrics:

python/sglang/srt/server_args.py

@@ -42,7 +42,6 @@ class ServerArgs:
     model_path: str
     tokenizer_path: Optional[str] = None
     tokenizer_mode: str = "auto"
-    skip_tokenizer_init: bool = False
     load_format: str = "auto"
     trust_remote_code: bool = True
     dtype: str = "auto"
@@ -54,6 +53,7 @@ class ServerArgs:
     chat_template: Optional[str] = None
     is_embedding: bool = False
     revision: Optional[str] = None
+    skip_tokenizer_init: bool = False
     return_token_ids: bool = False
 
     # Port for the HTTP server
@@ -276,17 +276,6 @@ class ServerArgs:
             "tokenizer if available, and 'slow' will "
             "always use the slow tokenizer.",
         )
-        parser.add_argument(
-            "--skip-tokenizer-init",
-            action="store_true",
-            help="If set, skip init tokenizer and pass input_ids in generate request",
-        )
-        parser.add_argument(
-            "--return-token-ids",
-            action="store_true",
-            default=ServerArgs.return_token_ids,
-            help="Whether to return token IDs in the output, this may introduce additional overhead.",
-        )
         parser.add_argument(
             "--load-format",
             type=str,
@@ -394,6 +383,17 @@ class ServerArgs:
             "name, a tag name, or a commit id. If unspecified, will use "
             "the default version.",
         )
+        parser.add_argument(
+            "--skip-tokenizer-init",
+            action="store_true",
+            help="If set, skip init tokenizer and pass input_ids in generate request",
+        )
+        parser.add_argument(
+            "--return-token-ids",
+            action="store_true",
+            default=ServerArgs.return_token_ids,
+            help="Whether to return token IDs in the output, this may introduce additional overhead.",
+        )
 
         # Memory and scheduling
         parser.add_argument(