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 14, 05:30 UTC
[ROCm][Bugfix] Add missing parameter to ROCm backend (#26029)
Signed-off-by: Gregory Shtrasberg <Gregory.Shtrasberg@amd.com>
Gregory Shtrasberg committed
Oct 1, 2025 at 22:23 UTC
0b018d8baf1bf967db20c7b962dc5a5d65e24539
1 file changed
+1
vllm/v1/attention/backends/rocm_attn.py
+1
@@ -175,6 +175,7 @@ class RocmAttentionBackend(AttentionBackend):
175
block_size: int,
176
num_kv_heads: int,
177
head_size: int,
178
+ cache_dtype_str: str = "auto",
179
) -> tuple[int, ...]:
180
if block_size % 16 != 0:
181
raise ValueError("Block size must be a multiple of 16.")