[GH-ISSUE #13] Error with backend cuda #8

New issue

Closed

opened 2026-10-26 22:19:04 +00:00 by bsakaguchi · 0 comments

bsakaguchi commented

2026-10-26 22:19:04 +00:00

Owner

Originally created by @tuolaku on GitHub (Jan 7, 2026).
Original GitHub issue: https://github.com/Comfy-Org/comfy-kitchen/issues/13

Found comfy_kitchen backend eager: {'available': True, 'disabled': False, 'unavailable_reason': None, 'capabilities': ['apply_rope', 'apply_rope1', 'dequantize_nvfp4', 'dequantize_per_tensor_fp8', 'quantize_nvfp4', 'quantize_per_tensor_fp8', 'scaled_mm_nvfp4']}
Found comfy_kitchen backend triton: {'available': True, 'disabled': True, 'unavailable_reason': None, 'capabilities': ['apply_rope', 'apply_rope1', 'dequantize_nvfp4', 'dequantize_per_tensor_fp8', 'quantize_nvfp4', 'quantize_per_tensor_fp8']}
Found comfy_kitchen backend cuda: {'available': False, 'disabled': False, 'unavailable_reason': 'Module use of python312.dll conflicts with this version of Python.', 'capabilities': []}

python: 3.13
Cuda:13.0
pytorch:2.9.1
RTX 5090D

Originally created by @tuolaku on GitHub (Jan 7, 2026). Original GitHub issue: https://github.com/Comfy-Org/comfy-kitchen/issues/13 Found comfy_kitchen backend eager: {'available': True, 'disabled': False, 'unavailable_reason': None, 'capabilities': ['apply_rope', 'apply_rope1', 'dequantize_nvfp4', 'dequantize_per_tensor_fp8', 'quantize_nvfp4', 'quantize_per_tensor_fp8', 'scaled_mm_nvfp4']} Found comfy_kitchen backend triton: {'available': True, 'disabled': True, 'unavailable_reason': None, 'capabilities': ['apply_rope', 'apply_rope1', 'dequantize_nvfp4', 'dequantize_per_tensor_fp8', 'quantize_nvfp4', 'quantize_per_tensor_fp8']} Found comfy_kitchen backend cuda: {'available': False, 'disabled': False, 'unavailable_reason': 'Module use of **python312.dl**l conflicts with this version of Python.', 'capabilities': []} python: 3.13 Cuda:13.0 pytorch:2.9.1 RTX 5090D

bsakaguchi closed this issue

2026-10-26 22:19:04 +00:00

bsakaguchi referenced this issue

2026-10-26 22:20:08 +00:00

[PR #8] [MERGED] Bug fixes #77

bsakaguchi referenced this issue

2026-10-26 22:20:19 +00:00

[PR #37] [MERGED] Add support for int8 quantization backend #94