[Frontend] Use new Renderer for Completions and Tokenize API (#32863)

Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
This commit is contained in:
Cyrus Leung
2026-01-31 04:51:15 -08:00
committed by GitHub
parent 8980001c93
commit f0a1c8453a
64 changed files with 2116 additions and 2003 deletions
@@ -4,12 +4,14 @@ from typing import Any
from pydantic import BaseModel, Field
from vllm.config import ModelConfig
from vllm.entrypoints.openai.chat_completion.protocol import ChatCompletionLogProbs
from vllm.entrypoints.openai.engine.protocol import (
SamplingParams,
StreamOptions,
)
from vllm.logprobs import Logprob
from vllm.renderers import TokenizeParams
from vllm.utils import random_uuid
@@ -62,6 +64,12 @@ class GenerateRequest(BaseModel):
description="KVTransfer parameters used for disaggregated serving.",
)
def build_tok_params(self, model_config: ModelConfig) -> TokenizeParams:
return TokenizeParams(
max_total_tokens=None,
max_output_tokens=0,
)
class GenerateResponseChoice(BaseModel):
index: int