[Attention] Add trtllm diffusion attention backend with Skip-Softmax (#5283)

Signed-off-by: lishunyang12 <lishunyang03@gmail.com>
Co-authored-by: lishunyang12 <lishunyang03@gmail.com>
This commit is contained in:
SYLARandlishunyang12 authored and GitHub committed 2026-07-27 22:48:11 +08:00
1 parent 4dd1b47f47
commit 7762d664d8
24 files changed
+1512 -52

No files matched your search

+16
View File
@@ -28,6 +28,7 @@ class ForwardContext:
attn_metadata: dict[str, AttentionMetadata] | list[dict[str, AttentionMetadata]] | None = None
split_text_embed_in_sp: bool = False
denoise_step_idx: int | None = None
denoise_timestep: float | None = None
# Per-request reference latent for img2img DiT models (e.g. Ming)
ref_latent: torch.Tensor | None = None
# whether to split the text embed in sequence parallel, if True, the text embed will be split in sequence parallel
@@ -214,6 +215,21 @@ def set_forward_context_denoise_step_idx(step_idx: int | None) -> None:
_forward_context.denoise_step_idx = step_idx
class DenoiseProgressMixin:
def record_denoise_step(
self,
step_idx: int | None,
timestep=None,
scheduler=None,
) -> None:
set_forward_context_denoise_step_idx(step_idx)
if timestep is None or _forward_context is None:
return
scheduler = scheduler if scheduler is not None else getattr(self, "scheduler", None)
ntt = getattr(getattr(scheduler, "config", None), "num_train_timesteps", None)
_forward_context.denoise_timestep = float(timestep) / ntt if ntt else None
def set_forward_context_ref_latent(ref_latent: torch.Tensor | None) -> None:
"""Set the per-request reference latent on the active ForwardContext.