[Bugfix] Validate draft-token capacity in forward benchmark (#61809)

Signed-off-by: znzryb <znzryb34@gmail.com>
Co-authored-by: Woosuk Kwon <woosuk@inferact.ai>
This commit is contained in:
znzryb
2026-10-17 00:51:36 -07:00
committed by GitHub
co-authored by Woosuk Kwon
parent 5be4266f5c
commit ad2688ab30
3 changed files with 24 additions and 0 deletions
+13
View File
@@ -9,6 +9,7 @@ import numpy as np
import pytest
from vllm.benchmarks.forward.batch import build_batch
from vllm.benchmarks.forward.main import run_case
from vllm.benchmarks.forward.shapes import jitter_kv_lens, parse_case
from vllm.platforms import current_platform
@@ -84,6 +85,18 @@ def test_jitter_kv_lens():
jitter_kv_lens(case, 0, 1000, 0)
@pytest.mark.parametrize("capacity", [0, 2])
def test_bench_forward_rejects_oversized_verify(capacity):
"""Reject drafts beyond the runner's buffer before launching CUDA kernels."""
runner = SimpleNamespace(num_speculative_steps=capacity)
case = parse_case("verify=2*4@64:3")
with pytest.raises(
ValueError,
match=rf"Case 'verify' needs 3 draft tokens.*supports {capacity}",
):
run_case(runner, case, SimpleNamespace())
@pytest.mark.benchmark
# TODO(woosuk): Support ROCm and re-enable this test there.
@pytest.mark.skipif(