Disty0
|
ccf9deaf28
|
Move SDNQ to the top of the settings list
|
2025-05-26 18:30:50 +03:00 |
Disty0
|
4453efee76
|
Rename NNCF to SDNQ and rename quant schemes
|
2025-05-26 02:39:51 +03:00 |
Disty0
|
85f00f9edb
|
Enable dyn atten by default for ROCm
|
2025-05-23 18:24:50 +03:00 |
Vladimir Mandic
|
4157336238
|
rename vae
Signed-off-by: Vladimir Mandic <mandic00@live.com>
|
2025-05-15 08:59:49 -04:00 |
Disty0
|
18c10883b8
|
Move NNCF above in the settings list
|
2025-05-14 05:19:11 +03:00 |
Disty0
|
f4e3a81a84
|
NNCF experimental direct INT8 MatMul support
|
2025-05-12 21:41:49 +03:00 |
Vladimir Mandic
|
91080f349f
|
latent-diffusion-upscale n-steps
Signed-off-by: Vladimir Mandic <mandic00@live.com>
|
2025-05-12 11:12:36 -04:00 |
Disty0
|
4eedeab9f8
|
NNCF use group size instead of number of groups and set default group size for int4 to 64
|
2025-05-11 20:38:01 +03:00 |
Disty0
|
0673689d5b
|
NNCF set the default group size to 128 for INT4
|
2025-05-11 08:45:27 +03:00 |
Disty0
|
03a6d7f9bf
|
NNCF add number of quantization groups
|
2025-05-11 05:55:58 +03:00 |
Disty0
|
b0e5a6c4df
|
Add devices.has_triton() and enable NNCF compile if triton is available
|
2025-05-09 22:24:36 +03:00 |
Disty0
|
a4d4462e2a
|
NNCF add decompress using toch.compile option
|
2025-05-09 21:02:24 +03:00 |
Seunghoon Lee
|
45c0bd6ec6
|
basic windows native pytorch support
|
2025-05-09 22:23:07 +09:00 |
Vladimir Mandic
|
808462fdab
|
update changelog
Signed-off-by: Vladimir Mandic <mandic00@live.com>
|
2025-05-09 08:18:40 -04:00 |
Vladimir Mandic
|
55b1cb8c8b
|
lower default teacache threshold
Signed-off-by: Vladimir Mandic <mandic00@live.com>
|
2025-05-08 10:14:15 -04:00 |
Disty0
|
dfebc909eb
|
Disable cuDNN benchmark on ROCm and add cudnn_benchmark_limit option
|
2025-05-08 13:27:06 +03:00 |
Disty0
|
a57c7087b8
|
Make NNCF INT4 quant run 75% faster and don't force fp32 decompress
|
2025-05-07 20:34:07 +03:00 |
Vladimir Mandic
|
5261c55890
|
fix lora legacy disabled
Signed-off-by: Vladimir Mandic <mandic00@live.com>
|
2025-05-07 11:48:21 -04:00 |
Disty0
|
f4dfe20bc1
|
Add sigmoid beta scheduler
|
2025-05-04 17:42:22 +03:00 |
Vladimir Mandic
|
473f394f97
|
fix save style
Signed-off-by: Vladimir Mandic <mandic00@live.com>
|
2025-04-30 09:18:41 -04:00 |
Vladimir Mandic
|
ff649291b5
|
lint fixes
Signed-off-by: Vladimir Mandic <mandic00@live.com>
|
2025-04-28 10:55:21 -04:00 |
Vladimir Mandic
|
1b341dd809
|
setting to enable/disable clip skip editing
Signed-off-by: Vladimir Mandic <mandic00@live.com>
|
2025-04-28 09:44:51 -04:00 |
Vladimir Mandic
|
5b68979226
|
update option names
Signed-off-by: Vladimir Mandic <mandic00@live.com>
|
2025-04-26 13:46:33 -04:00 |
Vladimir Mandic
|
5647d782f8
|
configurable restore metadata settings and params
Signed-off-by: Vladimir Mandic <mandic00@live.com>
|
2025-04-26 10:45:49 -04:00 |
Disty0
|
74d4093e74
|
NNCF disable quant conv by default
|
2025-04-23 16:31:27 +03:00 |
Vladimir Mandic
|
641e1e52b3
|
fix config save
Signed-off-by: Vladimir Mandic <mandic00@live.com>
|
2025-04-23 09:10:53 -04:00 |
Disty0
|
bb0329f54f
|
Update and refactor NNCF and add more quant options
|
2025-04-23 02:03:30 +03:00 |
Disty0
|
2264d8087b
|
Pre-load support for NNCF
|
2025-04-22 04:35:36 +03:00 |
Disty0
|
4c5cbde1f5
|
Make ROCm listen to the gc config and set the minimum gc threshold to 1
|
2025-04-21 01:53:07 +03:00 |
Seunghoon Lee
|
712530341a
|
fix onnx
|
2025-04-19 13:25:05 +09:00 |
Vladimir Mandic
|
cbef571f90
|
svdquant and others stuff
Signed-off-by: Vladimir Mandic <mandic00@live.com>
|
2025-04-17 22:14:11 -04:00 |
Vladimir Mandic
|
75ebf1e196
|
hidream add llm info to metadata
Signed-off-by: Vladimir Mandic <mandic00@live.com>
|
2025-04-17 14:44:37 -04:00 |
Vladimir Mandic
|
15f8e70e89
|
add nunchaku prototype
Signed-off-by: Vladimir Mandic <mandic00@live.com>
|
2025-04-15 14:39:24 -04:00 |
Vladimir Mandic
|
59efc95e00
|
flux-cfgzero map autopipeline
Signed-off-by: Vladimir Mandic <mandic00@live.com>
|
2025-04-14 10:03:33 -04:00 |
Vladimir Mandic
|
4aa17ca745
|
networks regex pattern(s) for skip-scan
Signed-off-by: Vladimir Mandic <mandic00@live.com>
|
2025-04-13 09:10:11 -04:00 |
Vladimir Mandic
|
90415a7469
|
add cfgzero to additional pipelines
Signed-off-by: Vladimir Mandic <mandic00@live.com>
|
2025-04-13 07:56:32 -04:00 |
Vladimir Mandic
|
6f2891afbd
|
add cfgzero for flux
Signed-off-by: Vladimir Mandic <mandic00@live.com>
|
2025-04-12 19:20:27 -04:00 |
Vladimir Mandic
|
3533258980
|
hidream whitelist samplers
Signed-off-by: Vladimir Mandic <mandic00@live.com>
|
2025-04-11 22:32:57 -04:00 |
Vladimir Mandic
|
78d8bfeba7
|
hidream allow custom llama
Signed-off-by: Vladimir Mandic <mandic00@live.com>
|
2025-04-11 21:27:48 -04:00 |
Vladimir Mandic
|
0439e5652d
|
add shared.opts.device_map
Signed-off-by: Vladimir Mandic <mandic00@live.com>
|
2025-04-11 14:53:42 -04:00 |
Vladimir Mandic
|
92af0036c6
|
add hidream
Signed-off-by: Vladimir Mandic <mandic00@live.com>
|
2025-04-10 16:28:15 -04:00 |
Vladimir Mandic
|
dc9a64d00b
|
memmon detect gpu swapping
Signed-off-by: Vladimir Mandic <mandic00@live.com>
|
2025-04-07 08:59:54 -04:00 |
Vladimir Mandic
|
84a24fb681
|
lora restore weights to orig device on apply
Signed-off-by: Vladimir Mandic <mandic00@live.com>
|
2025-04-07 07:49:18 -04:00 |
Vladimir Mandic
|
f414ea1139
|
set offload default
Signed-off-by: Vladimir Mandic <mandic00@live.com>
|
2025-04-06 13:10:32 -04:00 |
Vladimir Mandic
|
8f95477ad2
|
add teacache for flux
Signed-off-by: Vladimir Mandic <mandic00@live.com>
|
2025-04-05 12:58:00 -04:00 |
Vladimir Mandic
|
7520be4874
|
styles resize and bring quick-ui forward on hover
Signed-off-by: Vladimir Mandic <mandic00@live.com>
|
2025-04-04 09:05:32 -04:00 |
Vladimir Mandic
|
cd8357f1f4
|
add detailer renoise feature
Signed-off-by: Vladimir Mandic <mandic00@live.com>
|
2025-04-03 21:12:58 -04:00 |
Vladimir Mandic
|
5bdc87b68a
|
fix server restart
Signed-off-by: Vladimir Mandic <mandic00@live.com>
|
2025-04-03 08:22:43 -04:00 |
Vladimir Mandic
|
760b41e99f
|
update requirements and changelog
Signed-off-by: Vladimir Mandic <mandic00@live.com>
|
2025-04-02 09:33:09 -04:00 |
Vladimir Mandic
|
032bd46de2
|
improve mp4 download
Signed-off-by: Vladimir Mandic <mandic00@live.com>
|
2025-04-01 13:39:47 -04:00 |
Vladimir Mandic
|
5906eb6792
|
lora apply on gpu vs cpu settings option
Signed-off-by: Vladimir Mandic <mandic00@live.com>
|
2025-04-01 13:39:47 -04:00 |
Vladimir Mandic
|
daec94a9e9
|
settings css improvements
Signed-off-by: Vladimir Mandic <mandic00@live.com>
|
2025-03-30 15:39:44 -04:00 |
Vladimir Mandic
|
a467e23d72
|
full ui-settings refactor
Signed-off-by: Vladimir Mandic <mandic00@live.com>
|
2025-03-30 15:04:17 -04:00 |
Vladimir Mandic
|
f4fdd496b9
|
more granular quantization modules options
Signed-off-by: Vladimir Mandic <mandic00@live.com>
|
2025-03-28 14:46:52 -04:00 |
Vladimir Mandic
|
d1c3b97c65
|
add prompt enhance
Signed-off-by: Vladimir Mandic <mandic00@live.com>
|
2025-03-28 14:05:28 -04:00 |
Vladimir Mandic
|
0d6301ff25
|
samplers add manual sigma adjustment
Signed-off-by: Vladimir Mandic <mandic00@live.com>
|
2025-03-27 16:26:11 -04:00 |
Vladimir Mandic
|
2c58d3b36c
|
fastercache and pyramidattentionbroadcast
Signed-off-by: Vladimir Mandic <mandic00@live.com>
|
2025-03-27 11:49:30 -04:00 |
Vladimir Mandic
|
46bc0834b1
|
video tab major update
Signed-off-by: Vladimir Mandic <mandic00@live.com>
|
2025-03-21 14:53:52 -04:00 |
Vladimir Mandic
|
4f56f4aa33
|
add new optimum-quanto on-the-fly and simplify quantization loading
Signed-off-by: Vladimir Mandic <mandic00@live.com>
|
2025-03-16 21:45:05 -04:00 |
Vladimir Mandic
|
942553a504
|
rename vae and unet none to default
Signed-off-by: Vladimir Mandic <mandic00@live.com>
|
2025-03-16 18:46:26 -04:00 |
Vladimir Mandic
|
a91c95870d
|
remote vae encode
Signed-off-by: Vladimir Mandic <mandic00@live.com>
|
2025-03-15 17:03:37 -04:00 |
Vladimir Mandic
|
dbfd59434f
|
add gemma3
Signed-off-by: Vladimir Mandic <mandic00@live.com>
|
2025-03-15 15:30:57 -04:00 |
Vladimir Mandic
|
f39ae70eed
|
remote vae support raw/png/jpg
Signed-off-by: Vladimir Mandic <mandic00@live.com>
|
2025-02-23 15:01:43 -05:00 |
Vladimir Mandic
|
80d9070f09
|
skip control ui for legacy extensions
Signed-off-by: Vladimir Mandic <mandic00@live.com>
|
2025-02-22 14:25:58 -05:00 |
Seunghoon Lee
|
3253ec9c99
|
zluda flash attention 2
|
2025-02-22 21:40:09 +09:00 |
Vladimir Mandic
|
bf61c189a1
|
logging improvements and configurable extensions folder
Signed-off-by: Vladimir Mandic <mandic00@live.com>
|
2025-02-20 12:54:53 -05:00 |
Vladimir Mandic
|
6cf445d317
|
add ras-sd35 experimental
Signed-off-by: Vladimir Mandic <mandic00@live.com>
|
2025-02-18 18:47:42 -05:00 |
Vladimir Mandic
|
a4b3dc269e
|
modernize clip interrogate
Signed-off-by: Vladimir Mandic <mandic00@live.com>
|
2025-02-16 19:37:09 -05:00 |
Vladimir Mandic
|
5e12985c52
|
configurable request timeout
Signed-off-by: Vladimir Mandic <mandic00@live.com>
|
2025-02-16 17:54:21 -05:00 |
Vladimir Mandic
|
f3dd9b9646
|
vlm advanced settings and batch processing
Signed-off-by: Vladimir Mandic <mandic00@live.com>
|
2025-02-15 14:34:28 -05:00 |
Vladimir Mandic
|
e95bd93f67
|
caption ui redesign
Signed-off-by: Vladimir Mandic <mandic00@live.com>
|
2025-02-15 12:57:19 -05:00 |
Vladimir Mandic
|
1f2fc929f7
|
add joytag
Signed-off-by: Vladimir Mandic <mandic00@live.com>
|
2025-02-15 10:10:04 -05:00 |
Vladimir Mandic
|
dbf20d1388
|
api refactor: force access control and handle subpaths
Signed-off-by: Vladimir Mandic <mandic00@live.com>
|
2025-02-14 11:27:21 -05:00 |
Disty0
|
f94196bcd1
|
Rename ROCm Flash atten hijack to CK Flash atten and enable AOTriton memory and flash atten by default
|
2025-02-13 22:01:06 +03:00 |
Vladimir Mandic
|
49712ab9e7
|
update requirements
Signed-off-by: Vladimir Mandic <mandic00@live.com>
|
2025-02-13 12:03:08 -05:00 |
Vladimir Mandic
|
d9583df8de
|
modernui fix sampler advanced options
Signed-off-by: Vladimir Mandic <mandic00@live.com>
|
2025-02-12 16:28:17 -05:00 |
Vladimir Mandic
|
c608674fb0
|
styles support parsed and upparsed save and apply
Signed-off-by: Vladimir Mandic <mandic00@live.com>
|
2025-02-11 11:33:37 -05:00 |
Vladimir Mandic
|
92e7e74d00
|
persist hf and civitai tokens
Signed-off-by: Vladimir Mandic <mandic00@live.com>
|
2025-02-10 08:47:57 -05:00 |
Vladimir Mandic
|
d01fefdb30
|
add locale override capabilities
Signed-off-by: Vladimir Mandic <mandic00@live.com>
|
2025-02-09 09:27:06 -05:00 |
Disty0
|
a77bd98997
|
Don't force VAE compile with OpenVINO and set min detected memory for dyn atten to 4
|
2025-02-09 02:39:30 +03:00 |
Disty0
|
59911b776b
|
OpenVINO enable Upscaler compile by default
|
2025-02-09 01:33:20 +03:00 |
Vladimir Mandic
|
a19ec070cf
|
massive update to hints and add localization engine
Signed-off-by: Vladimir Mandic <mandic00@live.com>
|
2025-02-08 15:16:04 -05:00 |
Vladimir Mandic
|
8873b2f696
|
massive hints update
Signed-off-by: Vladimir Mandic <mandic00@live.com>
|
2025-02-08 15:16:04 -05:00 |
Vladimir Mandic
|
e018ed627d
|
ui quality-of-life improvements
Signed-off-by: Vladimir Mandic <mandic00@live.com>
|
2025-02-06 16:48:31 -05:00 |
Vladimir Mandic
|
2963ce127c
|
refactor interrogate/caption
Signed-off-by: Vladimir Mandic <mandic00@live.com>
|
2025-02-01 15:40:19 -05:00 |
Vladimir Mandic
|
654f44f66f
|
refactor interrogate/analyze/vqa code
Signed-off-by: Vladimir Mandic <mandic00@live.com>
|
2025-02-01 11:47:20 -05:00 |
Vladimir Mandic
|
8e03755d4b
|
add setting for prompt linebreaks
Signed-off-by: Vladimir Mandic <mandic00@live.com>
|
2025-02-01 09:41:52 -05:00 |
Disty0
|
64a5ca6471
|
Set default balanced offload min gpu memory to 0 on medvram and lowvram systems
|
2025-02-01 15:44:09 +03:00 |
Vladimir Mandic
|
7d9b268655
|
update repo links
Signed-off-by: Vladimir Mandic <mandic00@live.com>
|
2025-01-31 12:15:21 -05:00 |
Vladimir Mandic
|
61dd1fa122
|
improve networks visual search/filter
Signed-off-by: Vladimir Mandic <mandic00@live.com>
|
2025-01-31 11:15:09 -05:00 |
Vladimir Mandic
|
1697fb1508
|
add tunable ops path
Signed-off-by: Vladimir Mandic <mandic00@live.com>
|
2025-01-30 13:35:09 -05:00 |
Vladimir Mandic
|
0ea7840608
|
add tunable ops
Signed-off-by: Vladimir Mandic <mandic00@live.com>
|
2025-01-30 13:08:49 -05:00 |
Disty0
|
b141d266f6
|
Update dyn atten defaults
|
2025-01-29 00:31:00 +03:00 |
Vladimir Mandic
|
a7c0219577
|
pab: pyramid attention broadcast
Signed-off-by: Vladimir Mandic <mandic00@live.com>
|
2025-01-28 08:25:55 -05:00 |
Vladimir Mandic
|
79416af994
|
parse cgroups
Signed-off-by: Vladimir Mandic <mandic00@live.com>
|
2025-01-27 10:00:06 -05:00 |
Disty0
|
b0ecdf2f1c
|
Better dyn atten sdpa usage estimation logic
|
2025-01-26 16:57:26 +03:00 |
Disty0
|
bb07dd7a8f
|
Add trigger rate control to dyn atten
|
2025-01-26 03:48:01 +03:00 |
Vladimir Mandic
|
06ba03cf80
|
settings option to disable reference models
Signed-off-by: Vladimir Mandic <mandic00@live.com>
|
2025-01-23 15:19:43 -05:00 |
Vladimir Mandic
|
5a7c1f50c1
|
add native torch fp8 storage dtype
Signed-off-by: Vladimir Mandic <mandic00@live.com>
|
2025-01-23 12:07:08 -05:00 |
Disty0
|
40e7dcd5a4
|
OpenVINO add group_size option to compression
|
2025-01-23 00:15:27 +03:00 |
Vladimir Mandic
|
e9853ec0ca
|
add para-attention first-block-cache
Signed-off-by: Vladimir Mandic <mandic00@live.com>
|
2025-01-21 17:10:12 -05:00 |
Vladimir Mandic
|
e26de8cdba
|
detailer support for face restorer models
Signed-off-by: Vladimir Mandic <mandic00@live.com>
|
2025-01-18 14:29:40 -05:00 |
Vladimir Mandic
|
ae9b40c688
|
refactor to unify latent, resize and model based upscalers
Signed-off-by: Vladimir Mandic <mandic00@live.com>
|
2025-01-18 14:29:40 -05:00 |
Vladimir Mandic
|
bfe8ece749
|
unique font family registration
Signed-off-by: Vladimir Mandic <mandic00@live.com>
|
2025-01-17 16:20:46 -05:00 |
Vladimir Mandic
|
b22e3d66fc
|
update modernui
Signed-off-by: Vladimir Mandic <mandic00@live.com>
|
2025-01-17 09:19:00 -05:00 |
Vladimir Mandic
|
f69159ee53
|
fix log view
Signed-off-by: Vladimir Mandic <mandic00@live.com>
|
2025-01-15 13:11:35 -05:00 |
Vladimir Mandic
|
5a59054eec
|
refactor video file create and save
Signed-off-by: Vladimir Mandic <mandic00@live.com>
|
2025-01-15 13:03:40 -05:00 |
Vladimir Mandic
|
e4fbf5f0dc
|
fix hf cache setting override
Signed-off-by: Vladimir Mandic <mandic00@live.com>
|
2025-01-13 14:08:40 -05:00 |
Vladimir Mandic
|
0c8044070a
|
refactor: split legacy loaders
Signed-off-by: Vladimir Mandic <mandic00@live.com>
|
2025-01-13 13:00:30 -05:00 |
Vladimir Mandic
|
49f5c8ab12
|
refactor taesd and add multiple variants in settings
Signed-off-by: Vladimir Mandic <mandic00@live.com>
|
2025-01-12 14:09:55 -05:00 |
Vladimir Mandic
|
ca6092e9bc
|
fix flux controlnet
Signed-off-by: Vladimir Mandic <mandic00@live.com>
|
2025-01-11 18:21:11 -05:00 |
Disty0
|
705556d68d
|
JPEG XL support
|
2025-01-12 00:38:13 +03:00 |
Vladimir Mandic
|
e632031190
|
correct log message
Signed-off-by: Vladimir Mandic <mandic00@live.com>
|
2025-01-08 10:40:49 -05:00 |
Vladimir Mandic
|
7461507ecb
|
apply settings skip hidden
Signed-off-by: Vladimir Mandic <mandic00@live.com>
|
2025-01-07 11:04:34 -05:00 |
Vladimir Mandic
|
3d5cab66a7
|
settings debug
Signed-off-by: Vladimir Mandic <mandic00@live.com>
|
2025-01-07 10:32:32 -05:00 |
Vladimir Mandic
|
5593ea78a9
|
refactor detailer
Signed-off-by: Vladimir Mandic <mandic00@live.com>
|
2025-01-07 10:12:47 -05:00 |
Vladimir Mandic
|
17760cf75b
|
remove legacy restore resolution
Signed-off-by: Vladimir Mandic <mandic00@live.com>
|
2025-01-05 14:50:52 -05:00 |
Vladimir Mandic
|
9f30abbad5
|
fix scheduler api
Signed-off-by: Vladimir Mandic <mandic00@live.com>
|
2025-01-02 16:45:08 -05:00 |
Vladimir Mandic
|
5c5c7e0d51
|
fix vae tiling defaults
Signed-off-by: Vladimir Mandic <mandic00@live.com>
|
2025-01-01 15:48:30 -05:00 |
Vladimir Mandic
|
9f95fcc46e
|
first update in 2025
Signed-off-by: Vladimir Mandic <mandic00@live.com>
|
2025-01-01 09:49:12 -05:00 |
Vladimir Mandic
|
86ac38d94f
|
enable debug by default and optimize startup
Signed-off-by: Vladimir Mandic <mandic00@live.com>
|
2024-12-31 09:15:36 -05:00 |
Vladimir Mandic
|
7b7f121a96
|
sampler flow shift options and fix img2img
Signed-off-by: Vladimir Mandic <mandic00@live.com>
|
2024-12-27 16:33:19 -05:00 |
Vladimir Mandic
|
d49d470a89
|
hide disabled networks and add more previews
Signed-off-by: Vladimir Mandic <mandic00@live.com>
|
2024-12-27 09:45:03 -05:00 |
Vladimir Mandic
|
9cb15a564c
|
update vae tiling defaults and allow hypertile min size setting
Signed-off-by: Vladimir Mandic <mandic00@live.com>
|
2024-12-25 18:59:56 -05:00 |
Vladimir Mandic
|
e7f0047d52
|
add granular vae tiling options
Signed-off-by: Vladimir Mandic <mandic00@live.com>
|
2024-12-25 12:38:21 -05:00 |
Vladimir Mandic
|
7d663249e8
|
move postprocessing scripts to accordions
Signed-off-by: Vladimir Mandic <mandic00@live.com>
|
2024-12-23 12:23:18 -05:00 |
Disty0
|
6d3d23bddd
|
OpenVINO disable model caching by default
|
2024-12-23 00:16:34 +03:00 |
Vladimir Mandic
|
0803946c08
|
update changelog and cleanup
Signed-off-by: Vladimir Mandic <mandic00@live.com>
|
2024-12-19 11:34:19 -05:00 |
Vladimir Mandic
|
a7e0723dcf
|
profiling
Signed-off-by: Vladimir Mandic <mandic00@live.com>
|
2024-12-18 13:02:22 -05:00 |
Vladimir Mandic
|
fd7fe8cea5
|
add torchao
Signed-off-by: Vladimir Mandic <mandic00@live.com>
|
2024-12-17 13:29:36 -05:00 |
Vladimir Mandic
|
b1f1864099
|
lint updates
Signed-off-by: Vladimir Mandic <mandic00@live.com>
|
2024-12-15 13:12:35 -05:00 |
Vladimir Mandic
|
3e8dec9297
|
add freescale
Signed-off-by: Vladimir Mandic <mandic00@live.com>
|
2024-12-15 12:40:54 -05:00 |
Vladimir Mandic
|
e9f951b2c5
|
offload logging
Signed-off-by: Vladimir Mandic <mandic00@live.com>
|
2024-12-11 14:20:01 -05:00 |
Vladimir Mandic
|
c3b0c0a3bf
|
add SD_NO_CACHE env variable
Signed-off-by: Vladimir Mandic <mandic00@live.com>
|
2024-12-11 12:32:34 -05:00 |
Vladimir Mandic
|
9a588d9c91
|
update balanced offload
Signed-off-by: Vladimir Mandic <mandic00@live.com>
|
2024-12-11 12:06:03 -05:00 |
Vladimir Mandic
|
f4847f1b8a
|
optimize balanced offload
Signed-off-by: Vladimir Mandic <mandic00@live.com>
|
2024-12-10 15:49:20 -05:00 |
Vladimir Mandic
|
beea969fd3
|
update lora
Signed-off-by: Vladimir Mandic <mandic00@live.com>
|
2024-12-10 12:34:27 -05:00 |
Vladimir Mandic
|
944408e93b
|
warn on quanto with offload
Signed-off-by: Vladimir Mandic <mandic00@live.com>
|
2024-12-10 10:39:13 -05:00 |
Vladimir Mandic
|
042178fedb
|
reorg settings
Signed-off-by: Vladimir Mandic <mandic00@live.com>
|
2024-12-10 10:20:00 -05:00 |
Vladimir Mandic
|
1185950c4a
|
yet another lora refactor
Signed-off-by: Vladimir Mandic <mandic00@live.com>
|
2024-12-09 13:40:19 -05:00 |
AI-Casanova
|
6c9101dfaf
|
lora low memory mode: switching requires manual model reload
|
2024-12-06 22:54:08 -06:00 |
Vladimir Mandic
|
2965045993
|
change offload and upcast defaults
Signed-off-by: Vladimir Mandic <mandic00@live.com>
|
2024-12-05 07:58:55 -05:00 |
Vladimir Mandic
|
cfafa2b271
|
Merge branch 'dev' into lora-refactor
|
2024-12-02 11:23:15 -05:00 |
Vladimir Mandic
|
4eac263055
|
add bdia sampler
Signed-off-by: Vladimir Mandic <mandic00@live.com>
|
2024-12-02 11:21:39 -05:00 |
Vladimir Mandic
|
7e2034c4ff
|
lora add fuse
Signed-off-by: Vladimir Mandic <mandic00@live.com>
|
2024-12-02 10:51:41 -05:00 |
Disty0
|
82eb924486
|
Reduce balanced offload max gpu memory to 0.70
|
2024-12-02 00:29:01 +03:00 |
Vladimir Mandic
|
023b13b6cb
|
balanced offload improvements
Signed-off-by: Vladimir Mandic <mandic00@live.com>
|
2024-12-01 15:34:25 -05:00 |
Vladimir Mandic
|
b7aff134a2
|
add low/high threshold to balanced offload
Signed-off-by: Vladimir Mandic <mandic00@live.com>
|
2024-11-30 19:03:51 -05:00 |
Disty0
|
6ec93f2d46
|
Disable load lora gpu with medvram too
|
2024-11-30 17:04:35 +03:00 |
Disty0
|
63ba83d361
|
ZLUDA enable Dynamic attention by default
|
2024-11-30 01:15:49 +03:00 |