[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
@@ -29,7 +29,7 @@ from vllm.entrypoints.openai.engine.protocol import (
FunctionCall,
FunctionDefinition,
OpenAIBaseModel,
PerRequestTimingMetrics,
PerRequestMetrics,
StopParam,
StreamOptions,
ToolCall,
@@ -146,7 +146,7 @@ class ChatCompletionResponse(OpenAIBaseModel):
ec_transfer_params: dict[str, Any] | None = Field(
default=None, description="ECTransfer parameters."
)
metrics: PerRequestTimingMetrics | None = None
metrics: PerRequestMetrics | None = None
class ChatCompletionResponseStreamChoice(OpenAIBaseModel):
@@ -178,7 +178,7 @@ class ChatCompletionStreamResponse(OpenAIBaseModel):
# Rendered prompt text from chat templating (only set when
# ``return_prompt_text=True`` on the request); only sent on the first chunk.
prompt_text: str | None = None
metrics: PerRequestTimingMetrics | None = None
metrics: PerRequestMetrics | None = None
class ChatCompletionToolsParam(OpenAIBaseModel):