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>
38 lines
1.0 KiB
Python
38 lines
1.0 KiB
Python
# SPDX-License-Identifier: Apache-2.0
|
|
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
|
|
"""Math utility functions for vLLM."""
|
|
|
|
# Approximate value of 1/ln(2), used for log/exp base conversion
|
|
# Best FP32 approximation: 1.4426950216 (hex 0x3FB8AA3B)
|
|
RCP_LN2 = 1.4426950216
|
|
|
|
|
|
def cdiv(a: int, b: int) -> int:
|
|
"""Ceiling division."""
|
|
return -(a // -b)
|
|
|
|
|
|
def next_power_of_2(n: int) -> int:
|
|
"""The next power of 2 (inclusive)"""
|
|
return 1 if n < 1 else 1 << (n - 1).bit_length()
|
|
|
|
|
|
def prev_power_of_2(n: int) -> int:
|
|
"""The previous power of 2 (inclusive)"""
|
|
return 0 if n <= 0 else 1 << (n.bit_length() - 1)
|
|
|
|
|
|
def round_up(x: int, y: int) -> int:
|
|
"""Round up x to the nearest multiple of y."""
|
|
return ((x + y - 1) // y) * y
|
|
|
|
|
|
def round_down(x: int, y: int) -> int:
|
|
"""Round down x to the nearest multiple of y."""
|
|
return (x // y) * y
|
|
|
|
|
|
def largest_power_of_2_divisor(n: int) -> int:
|
|
"""Return the largest power-of-2 that divides *n* (isolate lowest set bit)."""
|
|
return n & (-n)
|