4917 commits

This branch

This branch

All branches

Author	SHA1	Message	Date
oobabooga	1972479610	Add the TP option to exllamav3_HF	2025-08-19 06:48:22 -07:00
oobabooga	e0f5905a97	Code formatting	2025-08-19 06:34:05 -07:00
oobabooga	5b06284a8a	UI: Keep ExLlamav3_HF selected if already selected for EXL3 models	2025-08-19 06:23:21 -07:00
oobabooga	cbba58bef9	UI: Fix code blocks having an extra empty line	2025-08-18 15:50:09 -07:00
oobabooga	8805a50d24	Update llama.cpp	2025-08-18 15:31:01 -07:00
oobabooga	7d23a55901	Fix model unloading when switching loaders (closes #7203)	2025-08-18 09:05:47 -07:00
oobabooga	08594e5263	Installer: Slight improvement	2025-08-18 05:59:46 -07:00
oobabooga	15f99b1b71	Installer: Fix a requirement file	2025-08-18 05:51:46 -07:00
oobabooga	6b1b2e2373	Update README	2025-08-17 22:19:20 -07:00
oobabooga	8a14aa62ff	Update README	2025-08-17 22:06:59 -07:00
oobabooga	8cdb911a6e	Update README	2025-08-17 22:06:12 -07:00
oobabooga	6bf31479d9	Update README	2025-08-17 22:00:21 -07:00
oobabooga	320f7339cd	Update README	2025-08-17 21:56:35 -07:00
oobabooga	3dec47eaf8	Small one-click installer changes	2025-08-17 21:43:46 -07:00
oobabooga	35707c2dd8	Update README	2025-08-17 21:39:57 -07:00
oobabooga	58797a9eb5	Minor change after 9651b5c873	2025-08-17 14:18:23 -07:00
oobabooga	64eba9576c	mtmd: Fix a bug when "include past attachments" is unchecked	2025-08-17 14:08:40 -07:00
oobabooga	3a91ca2dd1	Update flash attention	2025-08-17 13:57:23 -07:00
oobabooga	9651b5c873	Make CUDA 12.8 the default CUDA option, remove the CUDA 12.4 option ... Exllamav3 doesn't compile with torch 2.6 anymore, and torch 2.7 requires newer CUDA.	2025-08-17 13:26:09 -07:00
oobabooga	a633793a00	Bump exllamav3 to 0.0.6	2025-08-17 13:19:42 -07:00
oobabooga	dbabe67e77	ExLlamaV3: Enable the --enable-tp option, add a --tp-backend option	2025-08-17 13:19:11 -07:00
oobabooga	d771ca4a13	Fix web search (attempt)	2025-08-14 12:05:14 -07:00
oobabooga	73a8a737b2	docs: Improve the multimodal examples slightly	2025-08-13 18:23:18 -07:00
altoiddealer	57f6e9af5a	Set multimodal status during Model Loading (#7199)	2025-08-13 16:47:27 -03:00
oobabooga	725a8bcf60	Small docs change	2025-08-13 06:49:28 -07:00
oobabooga	331eab81f7	mtmd: Explain base64 inputs in the API docs	2025-08-13 06:46:10 -07:00
oobabooga	bd05fb899e	Update README	2025-08-12 14:19:18 -07:00
oobabooga	41b95e9ec3	Lint	2025-08-12 13:37:37 -07:00
oobabooga	2f979ce294	docs: Add a multimodal tutorial	2025-08-12 13:33:49 -07:00
oobabooga	7301452b41	UI: Minor info message change	2025-08-12 13:23:24 -07:00
oobabooga	8d7b88106a	Revert "mtmd: Fail early if images are provided but the model doesn't support them (llama.cpp)" ... This reverts commit d8fcc71616.	2025-08-12 13:20:16 -07:00
oobabooga	2f6a629393	UI: Minor improvement after 0e88a621fd	2025-08-12 08:51:01 -07:00
oobabooga	2238302b49	ExLlamaV3: Add speculative decoding	2025-08-12 08:50:45 -07:00
oobabooga	0882970a94	Update llama.cpp	2025-08-12 07:00:24 -07:00
oobabooga	d8fcc71616	mtmd: Fail early if images are provided but the model doesn't support them (llama.cpp)	2025-08-11 18:02:33 -07:00
oobabooga	e6447cd24a	mtmd: Update the llama-server request	2025-08-11 17:42:35 -07:00
oobabooga	c47e6deda2	Update README	2025-08-11 16:20:20 -07:00
oobabooga	0e3def449a	llama.cpp: --swa-full to llama-server when streaming-llm is checked	2025-08-11 15:17:25 -07:00
oobabooga	0e88a621fd	UI: Better organize the right sidebar	2025-08-11 15:16:03 -07:00
oobabooga	1e3c4e8bdb	Update llama.cpp	2025-08-11 14:40:59 -07:00
oobabooga	765af1ba17	API: Improve a validation	2025-08-11 12:39:48 -07:00
oobabooga	a78ca6ffcd	Remove a comment	2025-08-11 12:33:38 -07:00
oobabooga	dfd9c60d80	Merge remote-tracking branch 'refs/remotes/origin/dev' into dev	2025-08-11 12:33:27 -07:00
oobabooga	999471256c	Lint	2025-08-11 12:32:17 -07:00
Mykeehu	1ba1211ca0	Fix edit window and buttons in Messenger theme (#7100)	2025-08-11 16:13:56 -03:00
oobabooga	b10d525bf7	UI: Update a tooltip	2025-08-11 12:05:22 -07:00
oobabooga	b62c8845f3	mtmd: Fix /chat/completions for llama.cpp	2025-08-11 12:01:59 -07:00
oobabooga	38c0b4a1ad	Default ctx-size to 8192 when not found in the metadata	2025-08-11 07:39:53 -07:00
oobabooga	52d1cbbbe9	Fix an import	2025-08-11 07:38:39 -07:00
oobabooga	1cb800d392	Docs: small change	2025-08-11 07:37:10 -07:00