[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
+14
View File
@@ -20,6 +20,7 @@ from vllm.config import (
CompilationConfig,
KernelConfig,
ModelConfig,
ObservabilityConfig,
ParallelConfig,
PoolerConfig,
SchedulerConfig,
@@ -85,6 +86,19 @@ def test_kda_recoverssm_derivation_is_revalidated():
VllmConfig.validate_mamba_cached_kernel(config)
def test_per_request_spec_decode_metrics_requires_spec_decode():
# The flag only makes sense with speculative decoding configured; enabling
# it without --speculative-config should fail fast rather than silently
# produce no metrics.
for level in ("summary", "detailed"):
with pytest.raises(ValueError, match="speculative"):
VllmConfig(
observability_config=ObservabilityConfig(
per_request_spec_decode_metrics=level
)
)
def test_compile_config_repr_succeeds():
# setup: VllmBackend mutates the config object
config = VllmConfig()