[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
+5
View File
@@ -10,6 +10,7 @@ from vllm.config import (
ECTransferConfig,
KVTransferConfig,
ModelConfig,
ObservabilityConfig,
ParallelConfig,
SchedulerConfig,
SpeculativeConfig,
@@ -71,6 +72,7 @@ def create_scheduler(
ec_role: str | None = None,
use_v2_model_runner: bool | None = None,
kv_cache_spec: KVCacheSpec | None = None,
per_request_spec_decode_metrics: str = "none",
) -> Scheduler | AsyncScheduler:
"""Create scheduler under test.
@@ -175,6 +177,9 @@ def create_scheduler(
kv_transfer_config=kv_transfer_config,
speculative_config=speculative_config,
ec_transfer_config=ec_transfer_config,
observability_config=ObservabilityConfig(
per_request_spec_decode_metrics=per_request_spec_decode_metrics,
),
)
if kv_cache_spec is None:
kv_cache_spec = FullAttentionSpec(