nodes/viralvfx-ComfyUI-INT4-Fast
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Commit Graph

  • 970e85ea02 Fix static noise bug by dequantizing FP8 weights before INT4 quantization main viralvfx 2026-07-10 17:30:57 +05:30
  • d38dd4520c Fix: Support FP8 weights deferred on-the-fly quantization under AIMDO dynamic staging v1.0.5 viralvfx 2026-07-10 16:42:51 +05:30
  • df8197ebb3 Fix: Add missing QuantizedTensor import inside custom_state_dict_for_saving to resolve NameError v1.0.4 viralvfx 2026-07-10 16:34:11 +05:30
  • 5f1667705b Fix: Intercept state_dict_for_saving on ModelPatcher to correctly unpack QuantizedTensors during save v1.0.3 viralvfx 2026-07-10 16:28:54 +05:30
  • bd46f24974 Fix: Resolve Windows invalid buffer ERROR_INVALID_USER_BUFFER (os error 1784) during safetensors serialization v1.0.2 viralvfx 2026-07-10 16:25:08 +05:30
  • e8bc904f66 Chore: Add pyproject.toml configuration and release version 1.0.1 v1.0.1 viralvfx 2026-07-10 16:18:43 +05:30
  • 12fee3d270 Feat: Add support for FP8 weights on-the-fly quantization viralvfx 2026-07-10 16:17:49 +05:30
  • 80a65c4742 Doc: Add ComfyUI latest version requirement in README viralvfx 2026-07-10 13:01:39 +05:30
  • 39879ff2ed Doc: Update installation guide with git clone command in README viralvfx 2026-07-10 12:59:45 +05:30
  • 05d0f9baea Doc: Add note about first-run compilation in README viralvfx 2026-07-10 12:58:05 +05:30
  • ae53fbbace Doc: Add Krea2 Turbo INT4 verified model info in README viralvfx 2026-07-10 12:56:00 +05:30
  • 850cec79ef Initial commit: Standalone ComfyUI INT4 fast inference custom node viralvfx 2026-07-10 12:50:59 +05:30