github/ROCm
1
1
Fork 0
mirror of https://github.com/ROCm/ROCm.git synced 2026-04-05 03:01:17 -04:00
Code Issues Packages Projects Releases Wiki Activity

[FRONTEND] Correct error message (#1308)

Browse Source
This commit is contained in:
Sophia Wisdom
2023-03-09 21:14:11 -08:00
committed by GitHub
parent 902c61affb
commit a4a824a3c9
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
python/triton/ops/flash_attention.py
View File

@@ -198,7 +198,7 @@ class _attention(torch.autograd.Function):
# only support for Ampere now
capability = torch.cuda.get_device_capability()
if capability[0] < 8:
raise RuntimeError("Flash attention currently only supported for compute capability < 80")
raise RuntimeError("Flash attention currently only supported for compute capability >= 80")
BLOCK = 128
# shape constraints
Lq, Lk, Lv = q.shape[-1], k.shape[-1], v.shape[-1]