Gahow Wang
445e491123
third_party/vllm/ now tracked in git for direct patch management.
Based on vLLM v0.18.1 release with one patch applied:
vllm/v1/core/sched/scheduler.py:
Replace fatal assert with graceful skip when KV transfer callback
arrives for an already-aborted request during PD disaggregated serving.
Future vLLM modifications should be made directly in third_party/vllm/
and committed normally. The patches/ directory is kept as documentation
of what changed from upstream.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
31 lines
694 B
Python
31 lines
694 B
Python
# SPDX-License-Identifier: Apache-2.0
|
|
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
|
|
import subprocess
|
|
|
|
import pytest
|
|
|
|
MODEL_NAME = "meta-llama/Llama-3.2-1B-Instruct"
|
|
|
|
|
|
@pytest.mark.benchmark
|
|
def test_bench_throughput():
|
|
command = [
|
|
"vllm",
|
|
"bench",
|
|
"throughput",
|
|
"--model",
|
|
MODEL_NAME,
|
|
"--input-len",
|
|
"32",
|
|
"--output-len",
|
|
"1",
|
|
"--enforce-eager",
|
|
"--load-format",
|
|
"dummy",
|
|
]
|
|
result = subprocess.run(command, capture_output=True, text=True)
|
|
print(result.stdout)
|
|
print(result.stderr)
|
|
|
|
assert result.returncode == 0, f"Benchmark failed: {result.stderr}"
|