mirrors/ComfyUI
1
0
Fork 0
mirror of https://github.com/comfyanonymous/ComfyUI.git synced 2025-08-16 18:04:28 +00:00
Code Issues Packages Projects Releases Wiki Activity

Not sure if AMD actually support fp16 acc but it doesn't crash. (#9258)

Browse Source
This commit is contained in:
comfyanonymous 2025-08-09 09:49:25 -07:00 committed by GitHub
parent 735bb4bdb1
commit 5828607ccf
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
comfy/model_management.py
View File

@ -340,7 +340,7 @@ if ENABLE_PYTORCH_ATTENTION:
PRIORITIZE_FP16 = False # TODO: remove and replace with something that shows exactly which dtype is faster than the other PRIORITIZE_FP16 = False # TODO: remove and replace with something that shows exactly which dtype is faster than the other
try: try:
if is_nvidia() and PerformanceFeature.Fp16Accumulation in args.fast: if (is_nvidia() or is_amd()) and PerformanceFeature.Fp16Accumulation in args.fast:
torch.backends.cuda.matmul.allow_fp16_accumulation = True torch.backends.cuda.matmul.allow_fp16_accumulation = True
PRIORITIZE_FP16 = True # TODO: limit to cards where it actually boosts performance PRIORITIZE_FP16 = True # TODO: limit to cards where it actually boosts performance
logging.info("Enabled fp16 accumulation.") logging.info("Enabled fp16 accumulation.")