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>
40 lines
880 B
Python
40 lines
880 B
Python
# SPDX-License-Identifier: Apache-2.0
|
|
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
|
|
from abc import ABC
|
|
|
|
import numpy as np
|
|
|
|
from vllm.v1.kv_offload.abstract import LoadStoreSpec
|
|
|
|
|
|
class BlockIDsLoadStoreSpec(LoadStoreSpec, ABC):
|
|
"""
|
|
Spec for loading/storing KV blocks from given block numbers.
|
|
"""
|
|
|
|
def __init__(self, block_ids: list[int]):
|
|
self.block_ids = np.array(block_ids, dtype=np.int64)
|
|
|
|
def __repr__(self) -> str:
|
|
return repr(self.block_ids)
|
|
|
|
|
|
class GPULoadStoreSpec(BlockIDsLoadStoreSpec):
|
|
"""
|
|
Spec for loading/storing a KV block to GPU memory.
|
|
"""
|
|
|
|
@staticmethod
|
|
def medium() -> str:
|
|
return "GPU"
|
|
|
|
|
|
class CPULoadStoreSpec(BlockIDsLoadStoreSpec):
|
|
"""
|
|
Spec for loading/storing a KV block to CPU memory.
|
|
"""
|
|
|
|
@staticmethod
|
|
def medium() -> str:
|
|
return "CPU"
|