diff --git a/nanovllm/engine/block_manager.py b/nanovllm/engine/block_manager.py index 65d725e47..822b9341d 100644 --- a/nanovllm/engine/block_manager.py +++ b/nanovllm/engine/block_manager.py @@ -1,6 +1,6 @@ from collections import deque import xxhash -import numpy as np +import array from nanovllm.engine.sequence import Sequence @@ -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: