[Spec Decode][MRV2] Warm up top-k/top-p and greedy rejection kernels for speculative decoding (#59260)

Signed-off-by: zixi-qi <zixi@inferact.ai>
Co-authored-by: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
This commit is contained in:
qizixi
2026-10-14 14:59:21 -04:00
committed by GitHub
co-authored by Claude Opus 5.5 mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
parent ae94e9c9e8
commit c1407a7e86
3 changed files with 18 additions and 5 deletions
+1 -1
View File
@@ -76,7 +76,7 @@ def test_kernel_warmup_restores_uncalibrated_adaptive_manager(monkeypatch, fail_
rejection_sampler=rejection_sampler,
)
def run_steps(model_runner, execute, sample):
def run_steps(model_runner, execute, sample, greedy=False):
assert model_runner.adaptive_verification is None
assert not model_runner.rejection_sampler.enable_adaptive_verification
if fail_warmup: