[RL][Frontend] Return token-level weight-version spans on final outputs (#59582)

Signed-off-by: Shuolei Wang <shuoleiwang123@gmail.com>
Signed-off-by: Shuolei Wang <948904026@qq.com>
Co-authored-by: aoshen02 <aoshen@inferact.ai>
This commit is contained in:
Shuolei Wang
2026-10-11 11:33:29 +08:00
committed by GitHub
co-authored by aoshen02
parent 3c062d391d
commit b89852aad0
14 changed files with 169 additions and 28 deletions
@@ -31,6 +31,7 @@ from vllm.entrypoints.openai.completion.protocol import (
)
from vllm.entrypoints.serve.engine.protocol import UsageInfo
from vllm.logprobs import Logprob
from vllm.outputs import WeightVersionSpan
from vllm.renderers import TokenizeParams
from vllm.sampling_params import SamplingParams
from vllm.utils import random_uuid
@@ -411,6 +412,8 @@ class GenerateChoiceBase(BaseModel):
# or (b) `enable_return_routed_experts` is off server-side.
routed_experts: str | None = None
sampling_mask: list[list[int]] | None = None
# Contiguous weight version spans over output-token indexes.
weight_versions: list[WeightVersionSpan] | None = None
@field_validator("token_ids")
@classmethod
@@ -443,6 +446,8 @@ class GenerateStreamChoiceBase(BaseModel):
token_ids: list[int] | None = None
routed_experts: str | None = None
sampling_mask: list[list[int]] | None = None
# Set on the final chunk only; covers the whole output.
weight_versions: list[WeightVersionSpan] | None = None
class GenerateTokensStreamChoice(GenerateStreamChoiceBase):
@@ -453,6 +453,7 @@ class ServingTokens(GenerateBaseServing):
token_ids=as_list(output.token_ids),
routed_experts=routed_experts_b64,
sampling_mask=sampling_mask,
weight_versions=output.weight_versions,
)
if text_mode:
text_choices.append(
@@ -625,6 +626,7 @@ class ServingTokens(GenerateBaseServing):
token_ids=as_list(delta_token_ids),
routed_experts=routed_experts_b64,
sampling_mask=sampling_mask,
weight_versions=output.weight_versions,
)
chunk: GenerateTokensStreamResponse | GenerateTextStreamResponse
if text_mode: