You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@tvm.apache.org by an...@apache.org on 2022/08/10 20:31:55 UTC

[tvm] branch aluo/fix-int8-tensorcore created (now 7eab14aace)

This is an automated email from the ASF dual-hosted git repository.

andrewzhaoluo pushed a change to branch aluo/fix-int8-tensorcore
in repository https://gitbox.apache.org/repos/asf/tvm.git


      at 7eab14aace fix assert

This branch includes the following new commits:

     new 7eab14aace fix assert

The 1 revisions listed above as "new" are entirely new to this
repository and will be described in separate emails.  The revisions
listed as "add" were already present in the repository and have only
been added to this reference.



[tvm] 01/01: fix assert

Posted by an...@apache.org.
This is an automated email from the ASF dual-hosted git repository.

andrewzhaoluo pushed a commit to branch aluo/fix-int8-tensorcore
in repository https://gitbox.apache.org/repos/asf/tvm.git

commit 7eab14aace2c76cda9c4c1ee99e4c40f87c5d81c
Author: Andrew Zhao Luo <an...@gmail.com>
AuthorDate: Wed Aug 10 13:31:44 2022 -0700

    fix assert
---
 python/tvm/tir/tensor_intrin/cuda.py | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/python/tvm/tir/tensor_intrin/cuda.py b/python/tvm/tir/tensor_intrin/cuda.py
index 4ac9338ba8..b4f5d1d331 100644
--- a/python/tvm/tir/tensor_intrin/cuda.py
+++ b/python/tvm/tir/tensor_intrin/cuda.py
@@ -883,8 +883,8 @@ def get_wmma_intrin_group(
         A group of tensor intrinsics.
     """
     assert store_scope in ["global", "shared"]
-    assert in_dtype in ["float16"]
-    assert out_dtype in ["float16", "float32"]
+    assert in_dtype in ["float16", "int8"]
+    assert out_dtype in ["float16", "float32", "int32"]
 
     load_a_intrins = {
         "float16": WMMA_LOAD_16x16x16_F16_A_INTRIN,