[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:
+1
-1
@@ -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,
|
||||
|
||||
Reference in New Issue
Block a user