pollockjj-ComfyUI-MultiGPU

234 Commits 4 Branches 0 Tags

3 Commits

Include renames

Author	SHA1	Message	Date
John Pollock	54b7c5b0e6	Advanced Checkpoint and Advanced DisTorch2 Checkpoint loaders (https://github.com/pollockjj/ComfyUI-MultiGPU/issues/95 ), Fix CLiP loading device when MultGPU or DisTorch2 is invoked. Advanced Checkpoint Loaders allow users to map each of the elements of the checkpoint to a different device, or in the case of DisTorch2, shard the UNet and CLiP .safetensors arbitrarily whilst ensuring actual computation remains on selected `compute` device. Added example workflow for standard and DisTorch2 MultGPU checkpoint loaders.	2025-08-31 01:45:13 -05:00
John Pollock	4367c892d8	Eliminate unused safetensor loading analysis method and update example configurations, adding one with LoRAs as one of the tested configurations to avoid the issue seen during initial release.	2025-08-24 04:29:32 -05:00
John Pollock	545da7f741	Refactor: Reorganize and update example workflows This commit introduces a major reorganization of the `examples` directory to improve clarity and discoverability. Workflows are now grouped into subdirectories based on the features they demonstrate (e.g., `distorch`, `distorch2`, `gguf`, `multiGPU`). Key changes: - Moved existing example JSON files into new categorized folders. - Added several new and updated workflows, particularly for DisTorch2. - Removed outdated or redundant example files. - Renamed an internal function from `..._gguf_v2` to `..._safetensor_v2` to better reflect its broader functionality in DisTorch2.	2025-08-14 12:45:15 -05:00

Author

SHA1

Message

Date

John Pollock

54b7c5b0e6

Advanced Checkpoint and Advanced DisTorch2 Checkpoint loaders (https://github.com/pollockjj/ComfyUI-MultiGPU/issues/95 ), Fix CLiP loading device when MultGPU or DisTorch2 is invoked.

Advanced Checkpoint Loaders allow users to map each of the elements of the checkpoint to a different device, or in the case of DisTorch2, shard the UNet and CLiP .safetensors arbitrarily whilst ensuring actual computation remains on selected `compute` device.

Added example workflow for standard and DisTorch2 MultGPU checkpoint loaders.

2025-08-31 01:45:13 -05:00

John Pollock

4367c892d8

Eliminate unused safetensor loading analysis method and update example configurations, adding one with LoRAs as one of the tested configurations to avoid the issue seen during initial release.

2025-08-24 04:29:32 -05:00

John Pollock

545da7f741

Refactor: Reorganize and update example workflows

This commit introduces a major reorganization of the `examples` directory to improve clarity and discoverability. Workflows are now grouped into subdirectories based on the features they demonstrate (e.g., `distorch`, `distorch2`, `gguf`, `multiGPU`).

Key changes:
- Moved existing example JSON files into new categorized folders.
- Added several new and updated workflows, particularly for DisTorch2.
- Removed outdated or redundant example files.
- Renamed an internal function from `..._gguf_v2` to `..._safetensor_v2` to better reflect its broader functionality in DisTorch2.

2025-08-14 12:45:15 -05:00