4480 commits

This branch

This branch

All branches

Author	SHA1	Message	Date
Daniel Dengler	c25a381540	Add a "Branch here" footer button to chat messages (#6967)	2025-05-20 11:07:40 -03:00
oobabooga	8e10f9894a	Add a metadata field to the chat history & add date/time to chat messages (#7003)	2025-05-20 10:48:46 -03:00
oobabooga	9ec46b8c44	Remove the HQQ loader (HQQ models can be loaded through Transformers)	2025-05-19 09:23:24 -07:00
oobabooga	0c7237e4b7	Update README	2025-05-18 20:01:29 -07:00
oobabooga	bad1da99db	Merge remote-tracking branch 'refs/remotes/origin/dev' into dev	2025-05-18 14:09:08 -07:00
oobabooga	0c1bc6d1d0	Bump llama.cpp	2025-05-18 14:08:54 -07:00
Tiago Silva	9cd6ea6c0b	Fix Dockerfile in AMD and Intel (#6995)	2025-05-18 18:07:16 -03:00
oobabooga	83bfd5c64b	Fix API issues	2025-05-18 12:45:01 -07:00
oobabooga	126b3a768f	Revert "Dynamic Chat Message UI Update Speed (#6952)" (for now) ... This reverts commit 8137eb8ef4.	2025-05-18 12:38:36 -07:00
oobabooga	9d7a36356d	Remove unnecessary js that was causing scrolling issues	2025-05-18 10:56:16 -07:00
oobabooga	2faaf18f1f	Add back the "Common values" to the ctx-size slider	2025-05-18 09:06:20 -07:00
oobabooga	f1ec6c8662	Minor label changes	2025-05-18 09:04:51 -07:00
oobabooga	bd13a8f255	UI: Light theme improvement	2025-05-17 22:31:55 -07:00
oobabooga	076aa67963	Fix API issues	2025-05-17 22:22:18 -07:00
oobabooga	366de4b561	UI: Fix the chat area height when "Show controls" is unchecked	2025-05-17 17:11:38 -07:00
oobabooga	61276f6a37	Merge remote-tracking branch 'refs/remotes/origin/dev' into dev	2025-05-17 07:22:51 -07:00
oobabooga	4800d1d522	More robust VRAM calculation	2025-05-17 07:20:38 -07:00
mamei16	052c82b664	Fix KeyError: 'gpu_layers' when loading existing model settings (#6991)	2025-05-17 11:19:13 -03:00
oobabooga	0f77ff9670	UI: Use total VRAM (not free) for layers calculation when a model is loaded	2025-05-16 19:19:22 -07:00
oobabooga	4bf763e1d9	Multiple small CSS fixes	2025-05-16 18:22:43 -07:00
oobabooga	c0e295dd1d	Remove the 'None' option from the model menu	2025-05-16 17:53:20 -07:00
oobabooga	e3bba510d4	UI: Only add a blank space to streaming messages in instruct mode	2025-05-16 17:49:17 -07:00
oobabooga	71fa046c17	Minor changes after 1c549d176b	2025-05-16 17:38:08 -07:00
oobabooga	d99fb0a22a	Add backward compatibility with saved n_gpu_layers values	2025-05-16 17:29:18 -07:00
oobabooga	1c549d176b	Fix GPU layers slider: honor saved settings and show true maximum	2025-05-16 17:26:13 -07:00
oobabooga	e4d3f4449d	API: Fix a regression	2025-05-16 13:02:27 -07:00
oobabooga	470c822f44	API: Hide the uvicorn access logs from the terminal	2025-05-16 12:54:39 -07:00
oobabooga	adb975a380	Prevent fractional gpu-layers in the UI	2025-05-16 12:52:43 -07:00
oobabooga	fc483650b5	Set the maximum gpu_layers value automatically when the model is loaded with --model	2025-05-16 11:58:17 -07:00
oobabooga	38c50087fe	Prevent a crash on systems without an NVIDIA GPU	2025-05-16 11:55:30 -07:00
oobabooga	253e85a519	Only compute VRAM/GPU layers for llama.cpp models	2025-05-16 10:02:30 -07:00
oobabooga	9ec9b1bf83	Auto-adjust GPU layers after model unload to utilize freed VRAM	2025-05-16 09:56:23 -07:00
oobabooga	ee7b3028ac	Always cache GGUF metadata calls	2025-05-16 09:12:36 -07:00
oobabooga	4925c307cf	Auto-adjust GPU layers on context size and cache type changes + many fixes	2025-05-16 09:07:38 -07:00
oobabooga	93e1850a2c	Only show the VRAM info for llama.cpp	2025-05-15 21:42:15 -07:00
oobabooga	cbf4daf1c8	Hide the LoRA menu in portable mode	2025-05-15 21:21:54 -07:00
oobabooga	fd61297933	Lint	2025-05-15 21:19:19 -07:00
oobabooga	8cb73b78e1	Update ExLlamaV3	2025-05-15 20:10:34 -07:00
oobabooga	041248cc9f	Update llama.cpp	2025-05-15 20:10:02 -07:00
oobabooga	5534d01da0	Estimate the VRAM for GGUF models + autoset gpu-layers (#6980)	2025-05-16 00:07:37 -03:00
oobabooga	c4a715fd1e	UI: Move the LoRA menu under "Other options"	2025-05-13 20:14:09 -07:00
oobabooga	035cd3e2a9	UI: Hide the extension install menu in portable builds	2025-05-13 20:09:22 -07:00
oobabooga	2826c60044	Use logger for "Output generated in ..." messages	2025-05-13 14:45:46 -07:00
oobabooga	3fa1a899ae	UI: Fix gpu-layers being ignored (closes #6973)	2025-05-13 12:07:59 -07:00
oobabooga	c375b69413	API: Fix llama.cpp generating after disconnect, improve disconnect detection, fix deadlock on simultaneous requests	2025-05-13 11:23:33 -07:00
oobabooga	62c774bf24	Revert "New attempt" ... This reverts commit e7ac06c169.	2025-05-13 06:42:25 -07:00
oobabooga	e7ac06c169	New attempt	2025-05-10 19:20:04 -07:00
oobabooga	0c5fa3728e	Revert "Fix API failing to cancel streams (attempt), closes #6966" ... This reverts commit 006a866079.	2025-05-10 19:12:40 -07:00
oobabooga	006a866079	Fix API failing to cancel streams (attempt), closes #6966	2025-05-10 17:55:48 -07:00
oobabooga	47d4758509	Fix #6970	2025-05-10 17:46:00 -07:00