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>
14 lines
390 B
Python
14 lines
390 B
Python
# SPDX-License-Identifier: Apache-2.0
|
|
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
|
|
MB_bytes = 1_000_000
|
|
"""The number of bytes in one megabyte (MB)."""
|
|
|
|
MiB_bytes = 1 << 20
|
|
"""The number of bytes in one mebibyte (MiB)."""
|
|
|
|
GB_bytes = 1_000_000_000
|
|
"""The number of bytes in one gigabyte (GB)."""
|
|
|
|
GiB_bytes = 1 << 30
|
|
"""The number of bytes in one gibibyte (GiB)."""
|