A high-throughput and memory-efficient inference and serving engine for LLMs
Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git
Synced Nov 15, 06:00 UTC
[MISC] correct copy_blocks src_to_dists param type (#19696)
Signed-off-by: Andy Xie <andy.xning@gmail.com>
Ning Xie committed
Jun 18, 2025 at 08:21 UTC
c53711bd63dba1945c45f654b9f8e0776b02f7f2
1 file changed
+2
-2
vllm/attention/ops/ipex_attn.py
+2
-2
@@ -1,7 +1,7 @@
1
# SPDX-License-Identifier: Apache-2.0
2
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
3
4
-from typing import Dict, List, Optional, Tuple
4
+from typing import List, Optional, Tuple
5
6
try:
7
import intel_extension_for_pytorch.llm.modules as ipex_modules
@@ -120,7 +120,7 @@ class _PagedAttention:
120
@staticmethod
121
def copy_blocks(
122
kv_caches: List[torch.Tensor],
123
- src_to_dists: Dict[int, List[int]],
123
+ src_to_dists: torch.Tensor,
124
*args,
125
) -> None:
126
key_caches = [kv_cache[0] for kv_cache in kv_caches]