68 commits

Author	SHA1	Message	Date
oobabooga	fd41f2fafc	Update llama.cpp	2025-08-22 11:18:56 -07:00
oobabooga	8805a50d24	Update llama.cpp	2025-08-18 15:31:01 -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	0882970a94	Update llama.cpp	2025-08-12 07:00:24 -07:00
oobabooga	1e3c4e8bdb	Update llama.cpp	2025-08-11 14:40:59 -07:00
oobabooga	eb16f64017	Update llama.cpp	2025-08-09 17:12:16 -07:00
oobabooga	f1147c9926	Update llama.cpp	2025-08-06 19:32:36 -07:00
oobabooga	42e3a7a5ae	Update llama.cpp	2025-08-05 14:56:12 -07:00
oobabooga	02a3420a50	Bump transformers to 4.55 (adds gpt-oss support)	2025-08-05 10:09:30 -07:00
oobabooga	74230f559a	Bump transformers to 4.54	2025-08-01 11:03:15 -07:00
oobabooga	ccf5e3e3a7	Update exllamav3	2025-07-19 12:07:38 -07:00
oobabooga	a00983b2ba	Update llama.cpp	2025-07-19 12:07:20 -07:00
oobabooga	9371867238	Update exllamav2	2025-07-15 07:38:03 -07:00
oobabooga	03fb85e49a	Update llama.cpp	2025-07-15 07:37:13 -07:00
oobabooga	5a8a9c22e8	Update llama.cpp	2025-07-11 09:20:27 -07:00
oobabooga	0f3a88057c	Don't downgrade triton-windows on CUDA 12.8	2025-07-10 05:39:04 -07:00
oobabooga	e523f25b9f	Downgrade triton-windows to 3.2.0.post19 ... https://github.com/oobabooga/text-generation-webui/issues/7107#issuecomment-3057250374	2025-07-10 05:35:57 -07:00
oobabooga	a7a3a0c700	Merge remote-tracking branch 'refs/remotes/origin/dev' into dev	2025-07-09 21:07:42 -07:00
oobabooga	21e0e9f32b	Add the triton-windows requirement on Windows to make transformers functional	2025-07-09 21:05:17 -07:00
dependabot[bot]	d1f4622a96	Update peft requirement from ==0.15.* to ==0.16.* in /requirements/full (#7127)	2025-07-10 00:15:50 -03:00
oobabooga	8b3c7aa795	Bump bitsandbytes to 0.46	2025-07-09 19:46:55 -07:00
oobabooga	f045b72826	Bump accelerate to 1.8	2025-07-09 19:46:26 -07:00
oobabooga	c357601c01	Bump transformers to 4.53	2025-07-09 18:48:04 -07:00
oobabooga	e52bc0acb2	Update llama.cpp	2025-07-06 20:28:35 -07:00
oobabooga	de4ccffff8	Fix the duckduckgo search	2025-07-06 16:24:57 -07:00
oobabooga	c4d738f39f	Update llama.cpp	2025-07-05 14:09:29 -07:00
oobabooga	23bb94a5fb	Update llama.cpp	2025-07-03 20:36:54 -07:00
oobabooga	93cd47c948	Bump numpy to 2.2 (loses #7090)	2025-06-19 08:00:30 -07:00
oobabooga	315e06f695	Update llama.cpp	2025-06-17 07:51:16 -07:00
oobabooga	e8dc7b0ee9	Bump exllamav3 to 0.0.4	2025-06-15 08:15:29 -07:00
oobabooga	ad0be25c46	Update llama.cpp	2025-06-14 15:00:14 -07:00
oobabooga	552cb09f09	Do not bump Transformers to 4.52 on CUDA 12.8 ... Performance is slow, and the older version works fine with torch 2.7.	2025-06-10 18:45:42 -07:00
oobabooga	2dabdbc7da	Update llama.cpp	2025-06-10 05:25:23 -07:00
oobabooga	263b5d5557	Use html2text to extract the text of web searches without losing formatting	2025-06-09 17:55:26 -07:00
rakha abadi susilo	db847eed4c	Add RTX 50XX Nvidia blackwell support (ExLlamaV2/V3 and Transformers) (#7011) ... --------- Co-authored-by: oobabooga <112222186+oobabooga@users.noreply.github.com>	2025-06-07 21:44:15 -03:00
oobabooga	b38ec0ec38	Update llama.cpp	2025-06-02 11:33:17 -07:00
oobabooga	45c9ae312c	Use the flash-attention wheels in https://github.com/kingbri1/flash-attention	2025-06-01 22:17:22 -07:00
oobabooga	1d88456659	Add support for .docx attachments	2025-05-31 20:15:07 -07:00
oobabooga	dc8ed6dbe7	Bump exllamav3 to 0.0.3	2025-05-31 14:27:33 -07:00
oobabooga	c55d3c61c6	Bump exllamav2 to 0.3.1	2025-05-31 14:21:42 -07:00
oobabooga	28e6bd4fcd	Revert "Update transformers requirement in /requirements/full (#7017)" ... This reverts commit cc9b7253c1.	2025-05-29 14:49:07 -07:00
oobabooga	8078c41ec6	Revert "Bump llama.cpp" ... This reverts commit a8d02dec8f.	2025-05-29 13:32:19 -07:00
oobabooga	a8d02dec8f	Bump llama.cpp	2025-05-29 04:24:21 -07:00
oobabooga	077bbc6b10	Add web search support (#7023)	2025-05-28 04:27:28 -03:00
dependabot[bot]	cc9b7253c1	Update transformers requirement in /requirements/full (#7017)	2025-05-26 23:13:10 -03:00
oobabooga	409a48d6bd	Add attachments support (text files, PDF documents) (#7005)	2025-05-21 00:36:20 -03:00
oobabooga	51c50b265d	Update llama.cpp to b7a17463ec	2025-05-20 11:16:12 -07:00
oobabooga	0c1bc6d1d0	Bump llama.cpp	2025-05-18 14:08:54 -07:00