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>
28 lines
1.1 KiB
Python
28 lines
1.1 KiB
Python
# SPDX-License-Identifier: Apache-2.0
|
|
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
|
|
import numpy as np
|
|
import pytest
|
|
|
|
MODELS = ["google/gemma-2b", "google/gemma-2-2b", "google/gemma-3-4b-it"]
|
|
|
|
|
|
@pytest.mark.parametrize("model", MODELS)
|
|
def test_dummy_loader(vllm_runner, monkeypatch, model: str) -> None:
|
|
with monkeypatch.context() as m:
|
|
m.setenv("VLLM_ALLOW_INSECURE_SERIALIZATION", "1")
|
|
with vllm_runner(
|
|
model,
|
|
load_format="dummy",
|
|
) as llm:
|
|
if model == "google/gemma-3-4b-it":
|
|
normalizers = llm.llm.collective_rpc(
|
|
lambda self: self.model_runner.model.language_model.model.normalizer.cpu().item() # noqa: E501
|
|
)
|
|
config = llm.llm.llm_engine.model_config.hf_config.text_config
|
|
else:
|
|
normalizers = llm.llm.collective_rpc(
|
|
lambda self: self.model_runner.model.model.normalizer.cpu().item()
|
|
)
|
|
config = llm.llm.llm_engine.model_config.hf_config
|
|
assert np.allclose(normalizers, config.hidden_size**0.5, rtol=2e-3)
|