24 Commits

Author	SHA1	Message	Date
layerdiffusion	475524496d	revise	2024-08-19 18:54:54 -07:00
layerdiffusion	d7151b4dcd	add low vram warning	2024-08-19 11:08:01 -07:00
layerdiffusion	d38e560e42	Implement some rethinking about LoRA system ... 1. Add an option to allow users to use UNet in fp8/gguf but lora in fp16. 2. All FP16 loras do not need patch. Others will only patch again when lora weight change. 3. FP8 unet + fp16 lora are available (somewhat only available) in Forge now. This also solves some “LoRA too subtle” problems. 4. Significantly speed up all gguf models (in Async mode) by using independent thread (CUDA stream) to compute and dequant at the same time, even when low-bit weights are already on GPU. 5. View “online lora” as a module similar to ControlLoRA so that it is moved to GPU together with model when sampling, achieving significant speedup and perfect low VRAM management simultaneously.	2024-08-19 04:31:59 -07:00
layerdiffusion	ab4b0d5b58	fix some mem leak	2024-08-17 00:19:43 -07:00
layerdiffusion	394da01959	simplify	2024-08-16 04:55:01 -07:00
layerdiffusion	e36487ffa5	tune	2024-08-16 04:49:25 -07:00
lllyasviel	6e6e5c2162	do some profile on 3090	2024-08-16 04:43:19 -07:00
layerdiffusion	7c0f78e424	reduce cast	2024-08-16 03:59:59 -07:00
layerdiffusion	d8b83a9501	gguf preview	2024-08-15 00:03:32 -07:00
layerdiffusion	59790f2cb4	simplify codes	2024-08-14 20:48:39 -07:00
layerdiffusion	b31f81628f	Revert "simplify codes" ... This reverts commit 2cc5aa7a3e.	2024-08-14 20:39:00 -07:00
layerdiffusion	2cc5aa7a3e	simplify codes	2024-08-14 20:35:28 -07:00
layerdiffusion	aff742b597	speed up lora using cuda profile	2024-08-14 19:09:35 -07:00
lllyasviel	61f83dd610	support all flux models	2024-08-13 05:42:17 -07:00
layerdiffusion	f6ef105cb3	fix wrong print	2024-08-12 03:58:58 -07:00
layerdiffusion	a16ca5d057	fix amd	2024-08-11 17:53:08 -07:00
lllyasviel	cfa5242a75	forge 2.0.0 ... see also discussions	2024-08-10 19:24:19 -07:00
layerdiffusion	6f254f3599	revise stream	2024-08-08 20:18:56 -07:00
layerdiffusion	60c5aea11b	revise stream logics	2024-08-08 18:45:36 -07:00
layerdiffusion	e1df7a1bae	revise kernel	2024-08-07 17:24:22 -07:00
layerdiffusion	b57573c8da	Implement many kernels from scratch	2024-08-06 20:19:03 -07:00
lllyasviel	71c94799d1	diffusion in fp8 landed	2024-08-06 16:47:39 -07:00
layerdiffusion	318219bc9d	move file	2024-08-02 03:37:20 -07:00
layerdiffusion	bc9977a305	UNet from Scratch ... Now backend rewrite is about 50% finished. Estimated finish is in 72 hours. After that, many newer features will land.	2024-08-01 21:19:41 -07:00