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 17, 01:45 UTC
[ROCm][Hardware][AMD] Adding Navi21 to fallback to naive attention if Triton is not used (#4658)
alexeykondrat committed
May 18, 2024 at 01:09 UTC
c0724fc9150329d42abaf2f0f77dc8ca91d48acb
1 file changed
+3
-2
vllm/attention/backends/rocm_flash_attn.py
+3
-2
@@ -231,8 +231,9 @@ class ROCmFlashAttentionImpl(AttentionImpl):
231
self.attn_func = triton_attention
232
logger.debug("Using Triton FA in ROCmBackend")
233
else:
234
- # if not using triton, navi3x not use flash-attn either
235
- if torch.cuda.get_device_capability()[0] == 11:
234
+ # if not using triton, navi3x/navi21/navi10 do not use flash-attn
235
+ # either
236
+ if torch.cuda.get_device_capability()[0] != 9:
237
self.use_naive_attn = True
238
else:
239
try: