[Model][Hardware][AMD][Kernel] Part 2/2 -> Enable e2e QK Norm + RoPE + KV Cache runtime fusion for Qwen3-30B-A3B on ROCM_ATTN (#42755)
Signed-off-by: Jack Hu <Jack.Hu@amd.com> Signed-off-by: Jack Hu <jingxujaster@hotmail.com> Signed-off-by: Jack Hu <jack.hu@amd.com> Co-authored-by: Douglas Lehr <91553416+dllehr-amd@users.noreply.github.com>
This commit is contained in:
@@ -955,7 +955,8 @@ STABLE_TORCH_LIBRARY_FRAGMENT(_C_cache_ops, ops) {
|
||||
" Tensor! key_cache, Tensor! value_cache,"
|
||||
" Tensor slot_mapping,"
|
||||
" str kv_cache_dtype,"
|
||||
" Tensor k_scale, Tensor v_scale) -> ()");
|
||||
" Tensor k_scale, Tensor v_scale,"
|
||||
" bool interleaved_v=False) -> ()");
|
||||
|
||||
// Reshape the key and value tensors and cache them.
|
||||
ops.def(
|
||||
|
||||
Reference in New Issue
Block a user