[Auto Sync] Update serving_base.py, serving_chat.py, servin... (20250910) (#10282)

Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
Co-authored-by: cctry <shiyang@x.ai>
This commit is contained in:
Lianmin Zheng
2025-09-10 16:58:59 -07:00
committed by GitHub
parent f3b5db6ee8
commit 033b75f559
5 changed files with 33 additions and 14 deletions

View File

@@ -1,4 +1,6 @@
from typing import Any, Dict, List, Optional, Union
from __future__ import annotations
from typing import TYPE_CHECKING, Any, Dict, List, Optional, Union
from fastapi import Request
from fastapi.responses import ORJSONResponse
@@ -13,10 +15,12 @@ from sglang.srt.entrypoints.openai.protocol import (
)
from sglang.srt.entrypoints.openai.serving_base import OpenAIServingBase
from sglang.srt.managers.io_struct import EmbeddingReqInput
from sglang.srt.managers.template_manager import TemplateManager
from sglang.srt.managers.tokenizer_manager import TokenizerManager
from sglang.srt.parser.conversation import generate_embedding_convs
if TYPE_CHECKING:
from sglang.srt.managers.template_manager import TemplateManager
from sglang.srt.managers.tokenizer_manager import TokenizerManager
class OpenAIServingEmbedding(OpenAIServingBase):
"""Handler for v1/embeddings requests"""