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>
21 lines
497 B
Python
21 lines
497 B
Python
# SPDX-License-Identifier: Apache-2.0
|
|
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
|
|
|
|
from vllm.logger import init_logger
|
|
|
|
logger = init_logger(__name__)
|
|
|
|
|
|
try:
|
|
from tpu_inference.platforms import (
|
|
TpuPlatform as TpuInferencePlatform,
|
|
)
|
|
|
|
TpuPlatform = TpuInferencePlatform # type: ignore
|
|
USE_TPU_INFERENCE = True
|
|
except ImportError:
|
|
logger.error(
|
|
"tpu_inference not found, please install tpu_inference to run vllm on TPU"
|
|
)
|
|
pass
|