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>
13 lines
331 B
Python
13 lines
331 B
Python
# SPDX-License-Identifier: Apache-2.0
|
|
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
|
|
|
|
import pytest
|
|
from transformers import AutoTokenizer
|
|
|
|
from vllm.tokenizers import TokenizerLike
|
|
|
|
|
|
@pytest.fixture(scope="function")
|
|
def default_tokenizer() -> TokenizerLike:
|
|
return AutoTokenizer.from_pretrained("gpt2")
|