xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2026-07-09 11:07:16 +08:00
Code Issues Packages Projects Releases Wiki Activity

[ROCm][Bugfix] Add missing parameter to ROCm backend (#26029)

Browse Source 
Signed-off-by: Gregory Shtrasberg <Gregory.Shtrasberg@amd.com>
Signed-off-by: yewentao256 <zhyanwentao@126.com>
This commit is contained in:
Gregory Shtrasberg 2025-10-01 22:23:14 -04:00 committed by yewentao256
parent 2ae74a80af
commit 91e10c725c
1 changed files with 1 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
vllm/v1/attention/backends/rocm_attn.py
View File

@ -175,6 +175,7 @@ class RocmAttentionBackend(AttentionBackend):
block_size: int, block_size: int,
num_kv_heads: int, num_kv_heads: int,
head_size: int, head_size: int,
cache_dtype_str: str = "auto",
) -> tuple[int, ...]: ) -> tuple[int, ...]:
if block_size % 16 != 0: if block_size % 16 != 0:
raise ValueError("Block size must be a multiple of 16.") raise ValueError("Block size must be a multiple of 16.")