zlei6/ComfyUI
1
0
Fork 0
mirror of https://github.com/Comfy-Org/ComfyUI.git synced 2026-08-27 11:22:35 +08:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'master' into pysssss-model-db

Browse Source
This commit is contained in:
Jedrzej Kosinski
2025-08-11 14:09:21 -07:00
parent cd679129e3 2208aa616d
commit 3089936a2c
6 changed files with 10 additions and 11 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
comfy/lora.py
View File

@@ -301,6 +301,7 @@ def model_lora_keys_unet(model, key_map={}):
key_map["{}".format(key_lora)] = k
# Support transformer prefix format
key_map["transformer.{}".format(key_lora)] = k
key_map["lycoris_{}".format(key_lora.replace(".", "_"))] = k #SimpleTuner lycoris format
return key_map

8
comfy/model_management.py
View File

@@ -321,9 +321,9 @@ try:
if torch_version_numeric >= (2, 7): # works on 2.6 but doesn't actually seem to improve much
if any((a in arch) for a in ["gfx90a", "gfx942", "gfx1100", "gfx1101", "gfx1151"]): # TODO: more arches, TODO: gfx950
ENABLE_PYTORCH_ATTENTION = True
if torch_version_numeric >= (2, 8):
if any((a in arch) for a in ["gfx1201"]):
ENABLE_PYTORCH_ATTENTION = True
# if torch_version_numeric >= (2, 8):
# if any((a in arch) for a in ["gfx1201"]):
# ENABLE_PYTORCH_ATTENTION = True
if torch_version_numeric >= (2, 7) and rocm_version >= (6, 4):
if any((a in arch) for a in ["gfx1201", "gfx942", "gfx950"]): # TODO: more arches
SUPPORT_FP8_OPS = True
@@ -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
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
PRIORITIZE_FP16 = True # TODO: limit to cards where it actually boosts performance
logging.info("Enabled fp16 accumulation.")