Skip to content

Use math.prod instead of np.prod for trivial ops #14142

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 1 commit into from
Mar 4, 2025
Merged

Use math.prod instead of np.prod for trivial ops #14142

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 2 additions & 2 deletions vllm/worker/cache_engine.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,8 +1,8 @@
# SPDX-License-Identifier: Apache-2.0
"""CacheEngine class for managing the KV cache."""
from math import prod
from typing import List

import numpy as np
import torch

from vllm import envs
Expand Down Expand Up @@ -90,7 +90,7 @@ def _allocate_kv_cache(
# NOTE this assumption currently only holds for MLA so we only apply
# this optimization when `use_mla` is true
entry_shape = kv_cache_shape[2:]
entry_size = np.prod(entry_shape)
entry_size = prod(entry_shape)
alloc_entry_size = align_to_256bytes(entry_size, self.dtype)
alloc_shape = (*kv_cache_shape[:2], alloc_entry_size)
else:
Expand Down