wangbo/ComfyUI
1
0
Fork 0
mirror of https://github.com/comfyanonymous/ComfyUI.git synced 2026-01-20 19:30:20 +08:00
Code Issues Actions 16 Packages Projects Releases Wiki Activity

write better tx commentary

Browse Source
This commit is contained in:
Rattus 2026-01-13 19:38:36 +10:00
parent e2b440b25e
commit e2d29926a9
1 changed files with 4 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
comfy/ops.py
View File

@ -170,8 +170,11 @@ def cast_bias_weight_with_vbar(s, dtype, device, bias_dtype, non_blocking, compu
if pin is not None: if pin is not None:
xfer_dest = comfy.memory_management.interpret_gathered_like([ pin ], xfer_dest)[0] xfer_dest = comfy.memory_management.interpret_gathered_like([ pin ], xfer_dest)[0]
#FIXME: This might be the wrong thing to do. Some reading suggests the DMA engine
#is posted writes and the compute stream could just fire and forget here. That
#would save this sync and some stalling on the offload stream that is better off
#running ahead to the next layer to read.
if offload_stream is not None: if offload_stream is not None:
#FIXME: if post cast didnt do anything this sync is un-needed
offload_stream.wait_stream(comfy.model_management.current_stream(device)) offload_stream.wait_stream(comfy.model_management.current_stream(device))
comfy.model_management.cast_to(xfer_dest, device=pin.device, non_blocking=non_blocking, stream=offload_stream, r=pin) comfy.model_management.cast_to(xfer_dest, device=pin.device, non_blocking=non_blocking, stream=offload_stream, r=pin)