v4.3 update. (#2709)

* v4.3 update.

* Update the cute_dsl_api changelog's doc link

* Update version to 4.3.0

* Update the example link

* Update doc to encourage user to install DSL from requirements.txt

---------

Co-authored-by: Larry Wu <larwu@nvidia.com>
This commit is contained in:
Junkai-Wu
2025-10-21 14:26:30 -04:00
committed by GitHub
co-authored by Larry Wu
parent e6e2cc29f5
commit b1d6e2c9b3
244 changed files with 59272 additions and 10455 deletions
+30
View File
@@ -315,6 +315,12 @@ SM100_MMA_SHAPES_MXF8F6F4_DENSE_1SM = {
}
SM100_MMA_SHAPES_MXF8F6F4_SPARSE_1SM = {
(128, 128, 32): 0,
(128, 192, 32): 1,
(128, 256, 32): 0,
}
SM100_MMA_SHAPES_MXF8F6F4_DENSE_2SM = {
(256, 64, 32): 1,
(256, 128, 32): 0,
@@ -324,6 +330,15 @@ SM100_MMA_SHAPES_MXF8F6F4_DENSE_2SM = {
}
SM100_MMA_SHAPES_MXF8F6F4_SPARSE_2SM = {
(256, 128, 32): 0,
(256, 192, 32): 1,
(256, 256, 32): 0,
}
# MXF4NVF4
SM100_MMA_SHAPES_MXF4NVF4_DENSE_1SM = {
(128, 64, 64): 1,
@@ -332,6 +347,13 @@ SM100_MMA_SHAPES_MXF4NVF4_DENSE_1SM = {
(128, 256, 64): 0,
}
SM100_MMA_SHAPES_MXF4NVF4_SPARSE_1SM = {
(128, 128, 64): 0,
(128, 256, 64): 0,
}
SM100_MMA_SHAPES_MXF4NVF4_DENSE_2SM = {
# Multiples of 16 for N
(256, 64, 64): 1,
@@ -340,3 +362,11 @@ SM100_MMA_SHAPES_MXF4NVF4_DENSE_2SM = {
(256, 256, 64): 0,
}
SM100_MMA_SHAPES_MXF4NVF4_SPARSE_2SM = {
# Multiples of 16 for N
(256, 128, 64): 0,
(256, 256, 64): 0,
}