 City
|
69f0daffc5
|
Merge pull request #92 from city96/ops_refactor
Fix LoRA reloading, ops refactor, better lowvram speed, sd.cpp compat
|
2024-09-03 03:13:54 +02:00 |
|
|
City
|
929d15454d
|
Rename ggml_forward
Makes it clear that this is the same thing as comfy_cast_weights
|
2024-09-02 03:58:26 +02:00 |
|
|
City
|
35007f2659
|
Refactor model loading
Should make it more readable. Moved import under if to avoid changes to stuff in `tools` breaking normal models.
|
2024-09-02 03:44:07 +02:00 |
|
|
City
|
df3378da6b
|
Detect quant
|
2024-09-02 03:17:16 +02:00 |
|
|
City
|
cd343d1426
|
Merge pull request #80 from blepping/feat_load_stable_diffusion.cpp
Support loading u-net from stable-diffusion.cpp GGUF files
|
2024-09-02 02:51:40 +02:00 |
|
|
blepping
|
fa1671d63e
|
Sync with upstream
|
2024-09-01 18:44:31 -06:00 |
|
|
blepping
|
379175e7bf
|
Refactor tensor type checking a bit more
|
2024-09-01 18:30:47 -06:00 |
|
|
City
|
ba8ce44b4c
|
Rename move_patch function
|
2024-09-02 02:22:32 +02:00 |
|
|
blepping
|
e19fe8e898
|
Rename ggml_check_delegate to is_ggml_quantized, refactor accordingly
|
2024-09-01 18:04:31 -06:00 |
|
|
City
|
c7b902bf9a
|
Patch load/unload fix
May break other things. For some reason T5 decided to run on the CPU with this change, but only like once and I can't for the life of me reproduce it.
|
2024-09-02 02:00:10 +02:00 |
|
|
City
|
43427eff52
|
Better patch clear logic
Reduces RAM overhead
|
2024-09-02 01:37:16 +02:00 |
|
|
blepping
|
3bad1b4e04
|
Fix loading GGUF t5xxl
Can't use squeeze proj workaround for stable-diffusion.cpp SD15
|
2024-09-01 06:46:50 -06:00 |
|
|
blepping
|
a0cb97eceb
|
Add LayerNorm and GroupNorm ops
Delegate to superclass methods whenever possible
|
2024-09-01 05:25:32 -06:00 |
|
|
blepping
|
436ecb4913
|
Merge upstream ops_refactor
|
2024-09-01 03:02:59 -06:00 |
|
|
blepping
|
ed0702fefc
|
Merge branch 'city96:main' into feat_load_stable_diffusion.cpp
|
2024-09-01 02:47:16 -06:00 |
|
|
City
|
7f3ced6c3e
|
Consider FP8 as source
#91
|
2024-09-01 00:56:30 +02:00 |
|
|
City
|
6618801f1c
|
Don't dequantize token embed on load
|
2024-08-30 06:25:19 +02:00 |
|
|
City
|
c231239fdf
|
cleanup
Perf difference from `torch.tensor(tensor.data)` doesn't seem realistically measurable and the warning is annoying.
|
2024-08-30 03:47:52 +02:00 |
|
|
City
|
ec24e75d89
|
Remove unused check
|
2024-08-30 03:40:15 +02:00 |
|
|
City
|
f40b149bc5
|
Add BF16 support
|
2024-08-30 03:39:57 +02:00 |
|
|
City
|
826bd1804c
|
Make ops less jank
Also possibly faster. Ignore the massively increased system memory usage.
|
2024-08-30 03:25:57 +02:00 |
|
|
blepping
|
b88cb9a344
|
Remove require_prefix in gguf_sd_loader
|
2024-08-28 12:50:39 -06:00 |
|
|
blepping
|
e814fc1264
|
Revert ggml_tensor_name addition
|
2024-08-28 12:34:08 -06:00 |
|
|
City
|
abe5c6a6c9
|
Fix weights not being copied for lowvram patch
This can probably be improved since the weights themselves never need to be copied as they cannot be changed anyway.
|
2024-08-28 20:23:08 +02:00 |
|
|
blepping
|
f7d8fbe740
|
Workaround for stable-diffusion.cpp SDXL GGUF files
|
2024-08-28 11:56:51 -06:00 |
|
|
blepping
|
6ae0c733b0
|
Support loading u-net from stable-diffusion.cpp GGUF files
Small cleanups
|
2024-08-28 10:34:58 -06:00 |
|
|
City
|
3d9869240b
|
Always patch weight
Should help with #33
|
2024-08-28 17:12:24 +02:00 |
|
|
City
|
258742c369
|
Fix Conv2D with bias
|
2024-08-26 17:49:18 +02:00 |
|
|
City
|
a9f6359a23
|
Merge pull request #63 from blepping/feat_sd1_sdxl
Add support for SD1x and SDXL models
|
2024-08-25 23:46:43 +02:00 |
|
|
blepping
|
df6f1ab39c
|
Sync with upstream
|
2024-08-25 15:32:45 -06:00 |
|
|
City
|
bfecd32f8c
|
Rewrite llama.cpp patch
For #63
|
2024-08-25 22:32:55 +02:00 |
|
|
blepping
|
c1693d0f55
|
Use a GGUF array for orig shape metadata
|
2024-08-25 13:18:35 -06:00 |
|
|
blepping
|
0aec56ec4c
|
Split orig shape metadata into individual fields
|
2024-08-25 12:00:28 -06:00 |
|
|
blepping
|
7413de86e6
|
Revert tensor construction change in dequantize_tensor
Eliminate GGMLOpsLayer, include functionality in GGMLLayer
|
2024-08-25 10:35:39 -06:00 |
|
|
blepping
|
f3cf802dd6
|
Cleanups, refactoring
|
2024-08-25 07:53:19 -06:00 |
|
|
blepping
|
2832969aea
|
Sync with main
|
2024-08-25 04:35:52 -06:00 |
|
|
City
|
0ba6f64974
|
Advanced loader with optimizations
It may help with speed but it may also increase VRAM usage or degrade image quality.
Fastest would be target/target/true.
|
2024-08-24 18:39:34 +02:00 |
|
|
City
|
90a63c0c0e
|
Fix for Intel Arc
Deep dive & fix by @simonlui in #50
|
2024-08-24 08:17:06 +02:00 |
|
|
blepping
|
c93e622a19
|
SD1/SDXL fixes
|
2024-08-23 20:19:48 -06:00 |
|
|
blepping
|
489aaecf7a
|
Show the correct type when using fallback quantization
|
2024-08-23 12:37:31 -06:00 |
|
|
blepping
|
cea1b47ab3
|
Add support for SD1x and SDXL models
|
2024-08-23 11:59:21 -06:00 |
|
|
City
|
377862a06d
|
Cast to device
forgot this
|
2024-08-23 03:23:49 +02:00 |
|
|
City
|
3aafaf9133
|
Fix LoRA loading on new versions
Again
|
2024-08-23 03:20:15 +02:00 |
|
|
City
|
6b499ec49e
|
Hotfix to work as normal tensor
Fixes [ViT-L-14-BEST...] not working
|
2024-08-23 02:13:48 +02:00 |
|
|
City
|
1743f8f1fa
|
Update README.md
|
2024-08-22 21:37:13 +02:00 |
|
|
City
|
8d1fbbc456
|
K quant patch / instructions
#11
|
2024-08-21 06:31:40 +02:00 |
|
|
City
|
1ebce77a44
|
Fix for single CLIP Loader
#52
|
2024-08-20 18:14:07 +02:00 |
|
|
City
|
65c0ab15a8
|
Update README.md
|
2024-08-20 04:22:35 +02:00 |
|
|
City
|
5d7ffb582c
|
Merge pull request #49 from city96/gguf_tenc
GGUF Text Encoder support
|
2024-08-20 03:52:09 +02:00 |
|
|
City
|
e7906b43eb
|
Hotfix for missing text_projection in clip
Also adds the triple text encode node for the 5 people still using SD3
|
2024-08-20 03:38:59 +02:00 |
|