[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:
Jack Hu
2026-10-15 17:10:14 -07:00
committed by GitHub
co-authored by Douglas Lehr
parent af28c171f5
commit ef38e8d006
23 changed files with 701 additions and 205 deletions
+1 -1
View File
@@ -650,7 +650,7 @@ void reshape_and_cache(torch::stable::Tensor& key, torch::stable::Tensor& value,
torch::stable::Tensor& slot_mapping,
const std::string& kv_cache_dtype,
torch::stable::Tensor& k_scale,
torch::stable::Tensor& v_scale);
torch::stable::Tensor& v_scale, bool interleaved_v);
void reshape_and_cache_flash(
torch::stable::Tensor& key, torch::stable::Tensor& value,