Skip to content

refactor(block_manager): replace numpy with array for token ID hashing #180

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

Open
fly1989 wants to merge 1 commit into
base: main
Choose a base branch
from
+2 −2
Open

refactor(block_manager): replace numpy with array for token ID hashing #180

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 nanovllm/engine/block_manager.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,6 +1,6 @@
from collections import deque
import xxhash
import numpy as np
import array

from nanovllm.engine.sequence import Sequence

Expand Down Expand Up @@ -37,7 +37,7 @@ def compute_hash(cls, token_ids: list[int], prefix: int = -1):
h = xxhash.xxh64()
if prefix != -1:
h.update(prefix.to_bytes(8, "little"))
h.update(np.array(token_ids).tobytes())
h.update(array.array('i', token_ids).tobytes())
return h.intdigest()

def _allocate_block(self, block_id: int) -> Block:
Expand Down