You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@tvm.apache.org by GitBox <gi...@apache.org> on 2021/03/02 17:55:36 UTC
[GitHub] [tvm] comaniac commented on a change in pull request #7496: [Frontend,TOPI] Improve dynamism for BatchMatmul and Dense
comaniac commented on a change in pull request #7496:
URL: https://github.com/apache/tvm/pull/7496#discussion_r585784489
##########
File path: python/tvm/topi/cuda/dense.py
##########
@@ -42,11 +42,8 @@ def dense_cublas(cfg, data, weight, bias=None, out_dtype=None):
batch, in_dim = data.shape
out_dim, _ = weight.shape
matmul = cublas.matmul(data, weight, False, True)
- if isinstance(batch, int):
+ if isinstance(batch, int) and isinstance(in_dim, int) and isinstance(out_dim, int):
Review comment:
It usually happens when the shape comes from C++ via FFI, so it'd better to make sure we cover both cases.
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
users@infra.apache.org