[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:
@@ -122,6 +122,7 @@ def paged_attention_rocm(
|
||||
v_scale: torch.Tensor,
|
||||
fp8_out_scale: torch.Tensor | None = None,
|
||||
mfma_type: str = "fp8" if envs.VLLM_ROCM_FP8_MFMA_PAGE_ATTN else "f16",
|
||||
use_interleaved_v_cache: bool = False,
|
||||
) -> None:
|
||||
torch.ops._rocm_C.paged_attention(
|
||||
out,
|
||||
@@ -144,6 +145,7 @@ def paged_attention_rocm(
|
||||
v_scale,
|
||||
fp8_out_scale,
|
||||
mfma_type,
|
||||
use_interleaved_v_cache,
|
||||
)
|
||||
|
||||
|
||||
@@ -2554,6 +2556,7 @@ def reshape_and_cache(
|
||||
kv_cache_dtype: str,
|
||||
k_scale: torch.Tensor,
|
||||
v_scale: torch.Tensor,
|
||||
interleaved_v: bool = False,
|
||||
) -> None:
|
||||
torch.ops._C_cache_ops.reshape_and_cache(
|
||||
key,
|
||||
@@ -2564,6 +2567,7 @@ def reshape_and_cache(
|
||||
kv_cache_dtype,
|
||||
k_scale,
|
||||
v_scale,
|
||||
interleaved_v,
|
||||
)
|
||||
|
||||
|
||||
|
||||
Reference in New Issue
Block a user