Add padding support to wvSplitK solution for skinny GEMMs (#33762)

Signed-off-by: Hashem Hashemi <hashem.hashemi@amd.com>
2026-02-28 01:02:05 -08:00
parent 1e69c04887
commit 7600642eae
3 changed files with 289 additions and 444 deletions
--- a/vllm/model_executor/layers/utils.py
+++ b/vllm/model_executor/layers/utils.py
@@ -191,7 +191,6 @@ def rocm_unquantized_gemm_impl(
        and on_gfx9()
        and x.dtype in [torch.float16, torch.bfloat16]
        and k % 8 == 0
-        and x.is_contiguous()
    )

    if use_skinny is not True: