[Kernel] Fuse FP8 output quantization into merge_attn_states (#36518)

Signed-off-by: Carl You <4531192+carlyou@users.noreply.github.com>
This commit is contained in:
Carl Y
2026-04-03 01:47:04 +00:00
committed by GitHub
parent 1f5ec2889c
commit 3bc2734dd0
8 changed files with 516 additions and 70 deletions
+2
View File
@@ -265,6 +265,7 @@ def merge_attn_states(
suffix_lse: torch.Tensor,
output_lse: torch.Tensor | None = None,
prefill_tokens_with_context: int | None = None,
output_scale: torch.Tensor | None = None,
) -> None:
torch.ops._C.merge_attn_states(
output,
@@ -274,6 +275,7 @@ def merge_attn_states(
suffix_output,
suffix_lse,
prefill_tokens_with_context,
output_scale,
)