1981 commits

Author	SHA1	Message	Date
oobabooga	151b552bc3	Decrease the resolution step to allow for 1368	2025-12-01 18:24:02 -08:00
oobabooga	322aab3410	Increase the image_steps maximum	2025-12-01 18:20:47 -08:00
oobabooga	f46f49e26c	Initial Qwen-Image support	2025-12-01 18:18:15 -08:00
oobabooga	225b8c326b	Try to not break portable builds	2025-12-01 17:13:16 -08:00
oobabooga	5fb1380ac1	Handle URLs like https://huggingface.co/Qwen/Qwen-Image	2025-12-01 17:09:32 -08:00
oobabooga	7dfb6e9c57	Add quantization options (bnb and quanto)	2025-12-01 17:05:42 -08:00
oobabooga	a7808f7f42	Make filenames always have the same size	2025-12-01 16:06:02 -08:00
oobabooga	748e2e55fd	Add steps/second info to log message	2025-12-01 15:44:31 -08:00
oobabooga	6a7209a842	Add PNG metadata, add pagination to Gallery tab	2025-12-01 15:41:58 -08:00
oobabooga	b4738beaf8	Remove the seed UI element	2025-12-01 13:59:10 -08:00
oobabooga	9b07a83330	Populate the history gallery by default	2025-12-01 10:51:12 -08:00
oobabooga	e301dd231e	Remove some emojis	2025-12-01 10:49:22 -08:00
oobabooga	5b385dc546	Make the image galleries taller	2025-12-01 10:48:55 -08:00
oobabooga	b42192c2b7	Implement settings autosaving	2025-12-01 10:43:42 -08:00
oobabooga	41618cf799	Merge branch 'dev' into image_generation	2025-12-01 09:35:22 -08:00
oobabooga	5327bc9397	Update modules/shared.py ... Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>	2025-11-28 22:48:05 -03:00
oobabooga	cecb172d2c	Add the code for 4-bit quantization	2025-11-27 18:29:32 -08:00
oobabooga	742db85de0	Hardcode 8-bit quantization for now	2025-11-27 18:23:36 -08:00
oobabooga	822e74ac97	Lint	2025-11-27 18:15:15 -08:00
oobabooga	30d1f502aa	More informative download message	2025-11-27 16:37:03 -08:00
oobabooga	74eedf6050	Remove the CFG slider	2025-11-27 16:28:40 -08:00
oobabooga	9e33c6bfb7	Add missing files	2025-11-27 15:56:58 -08:00
oobabooga	666816a773	Small fixes	2025-11-27 15:48:53 -08:00
oobabooga	21f992e7f7	Organize the UI	2025-11-27 15:42:11 -08:00
oobabooga	148a5d1e44	Keep things more modular	2025-11-27 15:32:01 -08:00
oobabooga	0adda7a5c5	Lint	2025-11-27 14:39:21 -08:00
oobabooga	aa074409cb	Better events for the dimensions	2025-11-27 14:38:50 -08:00
oobabooga	be799ba8eb	Lint	2025-11-27 14:25:49 -08:00
oobabooga	a873692234	Image generation now functional	2025-11-27 14:24:35 -08:00
oobabooga	2f11b3040d	Add functions	2025-11-27 13:53:46 -08:00
oobabooga	aa63c612de	Progress on model loading	2025-11-27 13:46:54 -08:00
oobabooga	164c6fcdbf	Add the UI structure	2025-11-27 13:44:07 -08:00
oobabooga	4ad2ad468e	Add basic structure	2025-11-27 10:10:11 -08:00
GodEmperor785	400bb0694b	Add slider for --ubatch-size for llama.cpp loader, change defaults for better MoE performance (#7316)	2025-11-21 16:56:02 -03:00
oobabooga	8f0048663d	More modular HTML generator	2025-11-21 07:09:16 -08:00
oobabooga	0d4eff284c	Add a --cpu-moe model for llama.cpp	2025-11-19 05:23:43 -08:00
Trenten Miller	6871484398	fix: Rename 'evaluation_strategy' to 'eval_strategy' in training	2025-10-28 16:48:04 -03:00
oobabooga	a156ebbf76	Lint	2025-10-15 13:15:01 -07:00
oobabooga	c871d9cdbd	Revert "Same as 7f06aec3a1 but for exllamav3_hf" ... This reverts commit deb37b821b.	2025-10-15 13:05:41 -07:00
oobabooga	b5a6904c4a	Make --trust-remote-code immutable from the UI/API	2025-10-14 20:47:01 -07:00
mamei16	308e726e11	log error when llama-server request exceeds context size (#7263)	2025-10-12 23:00:11 -03:00
oobabooga	655c3e86e3	Fix "continue" missing an initial space in chat-instruct/chat modes	2025-10-11 17:00:25 -07:00
oobabooga	c7dd920dc8	Fix metadata leaking into branched chats	2025-10-11 14:12:05 -07:00
oobabooga	78ff21d512	Organize the --help message	2025-10-10 15:21:08 -07:00
oobabooga	0d03813e98	Update modules/chat.py ... Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>	2025-10-09 21:01:13 -03:00
oobabooga	deb37b821b	Same as 7f06aec3a1 but for exllamav3_hf	2025-10-09 13:02:38 -07:00
oobabooga	7f06aec3a1	exllamav3: Implement the logits function for /v1/internal/logits	2025-10-09 11:24:25 -07:00
oobabooga	218dc01b51	Add fallbacks after 93aa7b3ed3	2025-10-09 10:59:34 -07:00
oobabooga	282aa19189	Safer profile picture uploading	2025-10-09 09:26:35 -07:00
oobabooga	93aa7b3ed3	Better handle multigpu setups with transformers + bitsandbytes	2025-10-09 08:49:44 -07:00