Commit Graph
27 Commits
Author SHA1 Message Date
John Pollock de00faaa3d Fixes for DisTorch V2 LoRA loading as well as sticky allocations when using standard loader 2025-08-24 06:01:07 -05:00
John Pollock 6e4181a7bb Refactor: Remove debugging and memory audit utilities
This commit removes several utility modules used for debugging, memory inspection, and hardware information gathering. These tools are no longer required and their removal simplifies the codebase.

The following files have been deleted:
- `debug_utils.py`
- `device_memory_audit.py`
- `hardware_info.py`
- `model_sig.py`

Additionally, the call to log memory usage on startup has been removed from `__init__.py`.
2025-08-15 08:25:18 -05:00
John Pollock d1c88a7cdb feat(distorch): Add universal .safetensors support & memory-based distribution
This commit introduces DisTorch v2.0.0, a major overhaul that extends multi-device model distribution to standard `.safetensors` models.

Key changes include:

- **Universal `.safetensors` Support:** The core distribution logic is no longer limited to GGUF models. It now fully supports `.safetensors`, allowing any UNet supported by native Comfy loaders to have its layers distributed across multiple devices (GPUs and CPU/RAM).
2025-08-14 08:17:15 -05:00
John Pollock 79e9230f4c fix(gguf): correct missing type enum for CLIPLoaderGGUF and DualCLIPLoaderGGUF
Populate 'type' options by sourcing from core nodes to avoid drift:\n- CLIPLoaderGGUF now derives 'type' from nodes.CLIPLoader.INPUT_TYPES()\n- DualCLIPLoaderGGUF now derives 'type' from nodes.DualCLIPLoader.INPUT_TYPES()\nThis fixes missing or outdated 'type' options in GGUF Single and Dual CLIP loaders.\n\nchore: bump version to 1.8.2
2025-08-08 01:36:59 -05:00
John Pollock 7a08dd97d5 feat: Experimental XPU support
Add guarded Intel XPU support alongside CUDA:
- get_device_list now includes xpu:N when available
- device selection (model/text encoder) considers CUDA or XPU and validates devices
- DisTorch donor/offload selection includes xpu devices
Also: remove unused MergeFluxLoRAs node and mapping; delete tools/ and precompiled_binaries/; bump project version to 1.8.1.
2025-08-07 16:22:53 -05:00
John Pollock a6f13e5ff3 feat: update README and pyproject.toml for enhanced WanVideoWrapper integration and version bump to 1.8.0 2025-08-06 17:58:07 -05:00
John Pollock a05823ff0a feat: add CLIPVisionLoaderMultiGPU support and update version to 1.7.3 2025-04-17 18:43:01 -05:00
John Pollock 4ff9b80286 feat: add QuadrupleCLIPLoader / QuadrupleCLIPLoaderGGUF support and update version to 1.7.2 2025-04-17 17:00:20 -05:00
John Pollock b0159761e2 feat: add support for 'pixart' and 'wan' types in CLIPLoaderGGUF to match core class; update version to 1.7.1 2025-03-24 05:38:44 -05:00
John Pollock 2d81ef0a21 Support for kijai's ComfyUI-WanVideoWrapper 2025-03-23 13:40:05 -05:00
John Pollock 1bf9333fc7 chore: update version to 1.6.2 and fix description formatting in pyproject.toml 2025-02-12 12:18:13 -06:00
John Pollock a2093a4fc9 feat: add text encoder device handling, whereas CLIP can sometimes default to CPU, whereas using a DisTorch CLIP load you can load the layes on CPU buy use CUDA for processing. Especially helpful llava-llama 2025-02-12 11:51:58 -06:00
John Pollock 62646d3ca3 Push Distorch 2.0 Virtual VRAM release out to Comfy Registry 2025-02-07 22:00:48 -06:00
John Pollock 3679c268ac 🔧 BREAKING CHANGE: DiffSynth functionality has been temporarily removed while investigating device management issue (Having two GPUs with different amounts of VRAM leads to OOMs pollockjj/ComfyUI-MultiGPU#13).
If you were using nodes with DiffSynth in their name (like ...DiffSynthMultiGPU), please switch to the standard MultiGPU versions for now (e.g., ...MultiGPU). This change eliminates a device management issue that was affecting some Windows users.

See: https://github.com/pollockjj/ComfyUI-MultiGPU/issues/13

Most users won't be affected as this only impacts the DiffSynth variants of nodes.

If you need help modifying your workflows, please open an issue. Will revisit DiffSynth functionality once issue can be contained or worked-around

Update comfyregistry to 1.5.0 to reflect major change in functionality, in this case, a reduction.
2025-02-06 00:32:21 -06:00
John Pollock 005b5b1882 This release includes an embeddings adapter for the IP2V part of kijai's CLIP loader for HunyuanVideo. See examples. Bump version to 1.4.3 and update category for HunyuanVideoEmbeddingsAdapter to multigpu; enhance README with new workflow examples for HunyuanVideo GGUF-quantized models. 2025-01-29 11:55:16 -06:00
John Pollock 185ecc2ab5 Push fix to check_module_exists() to Comfy Registry, thanks @3dluvr 2025-01-29 05:16:45 -06:00
John Pollock 41e974f086 1.40 -->1.4.1
Pop 1.4 (DisTorch) to Comfy Registry
2025-01-28 15:41:13 -06:00
John Pollock ff7329298c feat: Releasing Hunyuan Video UNet device split support. Update project description and bump version to 1.4.0 2025-01-15 09:26:42 -06:00
John Pollock 20ba9d099c fix: Bump version to 1.3.1 and update icon URL to raw GitHub link 2025-01-12 11:17:47 -06:00
John Pollock 92652cf816 feat: Update project description to include CPU device selection and bump version to 1.3.0; add icon URL for ComfyUI-MultiGPU 2025-01-12 11:08:41 -06:00
John Pollock 116dd935f2 chore: Rename publish workflow file and update version to 1.2.1 in pyproject.toml 2025-01-05 16:03:53 -06:00
John Pollock 4611332d12 chore: Bump version to 1.2.0 in pyproject.toml 2025-01-04 19:44:05 -06:00
John Pollock d13f821547 Bump version to 1.1.0 and update README to reflect CPU offloading capabilities; rename example JSON for clarity 2024-12-27 04:54:21 -06:00
John Pollock 94cf7d9779 Update project description and version in pyproject.toml; add experimental audio model loaders in __init__.py 2024-12-26 08:30:27 -06:00
John Pollock 38e476e8da Update project description and version in pyproject.toml 2024-12-25 08:40:41 -06:00
pollockjj 924ea16c81 Update pyproject.toml
added my PublisherId
2024-12-24 10:44:01 -06:00
snomiao 5182bfe5e3 chore(pyproject): Add pyproject.toml for Custom Node Registry 2024-12-20 23:50:41 +00:00