v3.9 (#2185)

* v3.8 update x * fix blackwell gg * doc change * doc change * doc change --------- Co-authored-by: yuzhai <yuzhai@nvidia.com> Co-authored-by: Haicheng Wu <haichengw@nvidia.com> Co-authored-by: Haicheng Wu <57973641+hwu36@users.noreply.github.com>
2025-03-20 22:52:23 -07:00
parent 8c4d1dc47d
commit 62750a2b75
334 changed files with 91517 additions and 2656 deletions
--- a/python/pycute/int_tuple.py
+++ b/python/pycute/int_tuple.py
@@ -117,12 +117,7 @@ def shape_div(a, b):
      return shape_div(a, product(b))
    else:                              # "int" "int"
      assert a % b == 0 or b % a == 0
-      #return -(-a // b)      # Python exclusive impl: "//" is always floor div
-      if a % b == 0:
-        return a // b
-      else:
-        return signum(a*b)
-
+      return (a + b - 1) // b

 # Exclusive prefix product with output congruent to input a
 def prefix_product(a, init=1):