[kernel] Support W4A8 on Hopper (#23198)

Signed-off-by: czhu-cohere <conway.zhu@cohere.com>
2025-08-24 02:18:04 -04:00
parent a75277285b
commit e76e233540
12 changed files with 1128 additions and 7 deletions
--- a/benchmarks/kernels/weight_shapes.py
+++ b/benchmarks/kernels/weight_shapes.py
@@ -95,4 +95,10 @@ WEIGHT_SHAPES = {
        ([2048, 2816], 1),
        ([1408, 2048], 0),
    ],
+    "CohereLabs/c4ai-command-a-03-2025": [
+        ([12288, 14336], 1),
+        ([12288, 12288], 0),
+        ([12288, 73728], 1),
+        ([36864, 12288], 0),
+    ],
 }