[Frontend][Core][Spec Decode] Per-request acceptance stats in OpenAI API responses (#48915)

Signed-off-by: Matthew Kotila <7692737+matthewkotila@users.noreply.github.com>
Co-authored-by: Reed Meyerson <31574681+reed-meyerson@users.noreply.github.com>
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
This commit is contained in:
Matthew Kotila
2026-08-20 15:42:49 -07:00
committed by GitHub
co-authored by Reed Meyerson Claude Opus 4.8
parent 2f41c894e3
commit 7cfb97e337
25 changed files with 798 additions and 76 deletions
@@ -13,7 +13,7 @@ from vllm.config import ModelConfig
from vllm.entrypoints.openai.engine.protocol import (
AnyResponseFormat,
OpenAIBaseModel,
PerRequestTimingMetrics,
PerRequestMetrics,
StopParam,
StreamOptions,
UsageInfo,
@@ -660,7 +660,7 @@ class CompletionResponse(OpenAIBaseModel):
ec_transfer_params: dict[str, Any] | None = Field(
default=None, description="ECTransfer parameters."
)
metrics: PerRequestTimingMetrics | None = None
metrics: PerRequestMetrics | None = None
class CompletionResponseStreamChoice(OpenAIBaseModel):
@@ -692,4 +692,4 @@ class CompletionStreamResponse(OpenAIBaseModel):
# Set only on the final chunk of a stream to mirror non-streaming responses
# without the per-chunk serialization overhead.
system_fingerprint: str | None = None
metrics: PerRequestTimingMetrics | None = None
metrics: PerRequestMetrics | None = None