[Render] Add /derender endpoints for disaggregated postprocessing (#43606)

Signed-off-by: Martin Hickey <martin.hickey@ie.ibm.com>
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
Co-authored-by: Isotr0py <mozf@mail2.sysu.edu.cn>
This commit is contained in:
Martin Hickey
2026-06-13 13:55:33 +08:00
committed by GitHub
co-authored by Isotr0py
parent 1033ffac2e
commit 43f0e024bc
7 changed files with 898 additions and 9 deletions
@@ -46,6 +46,7 @@ from vllm.entrypoints.openai.engine.serving import (
GenerationError,
OpenAIServing,
clamp_prompt_logprobs,
format_token_id_placeholder,
)
from vllm.entrypoints.openai.models.serving import OpenAIServingModels
from vllm.entrypoints.serve.utils.api_utils import get_max_tokens, should_include_usage
@@ -1129,7 +1130,7 @@ class OpenAIServingChat(OpenAIServing):
step_top_logprobs = top_logprobs[i]
if step_top_logprobs is None or step_top_logprobs.get(token_id) is None:
if should_return_as_token_id:
token = f"token_id:{token_id}"
token = format_token_id_placeholder(token_id)
else:
if tokenizer is None:
raise ValueError(