25 Commits

Author	SHA1	Message	Date
Georgi Gerganov	2401a86193	common : handle mxfp4 enum ... ggml-ci	2025-08-18 19:15:25 +03:00
Georgi Gerganov	38e504ae02	common : remove old types ... ggml-ci	2024-12-10 18:33:03 +02:00
Georgi Gerganov	0c87736710	common : fix compile warning ... ggml-ci	2024-12-03 21:05:37 +02:00
Georgi Gerganov	336c10a4c3	examples : adapt to ggml.h changes (#0) ... ggml-ci	2024-09-20 22:03:57 +03:00
Georgi Gerganov	a20d7bf932	common : handle new quant types (#0)	2024-07-27 18:26:12 +03:00
Georgi Gerganov	e914da9147	ggml : resolve merge (#0) ... ggml-ci	2024-05-11 21:30:08 +03:00
Georgi Gerganov	236a991862	sync : adapt to CUDA changes (#0) ... ggml-ci	2024-03-27 13:20:00 +02:00
slaren	7652115c79	update examples and tests	2024-03-14 18:46:58 +02:00
Georgi Gerganov	9fb1f17a51	sync : llama.cpp (#0)	2024-02-28 12:59:11 +02:00
Georgi Gerganov	582d85ba7b	sync : llama.cpp (#0)	2024-02-25 19:58:06 +02:00
Georgi Gerganov	30805514e1	sync : llama.cpp (#0) ... ggml-ci	2024-02-21 16:45:48 +02:00
Georgi Gerganov	5852e53104	common : add IQ1_S (#0) ... ggml-ci	2024-02-19 15:52:51 +02:00
Georgi Gerganov	d12ec3b512	sync : ggml (whisper/0)	2024-02-10 09:59:34 +02:00
Georgi Gerganov	bca51b5288	sync : llama.cpp	2024-01-14 10:49:50 +02:00
Georgi Gerganov	db02388c05	sync : ggml	2024-01-11 21:55:41 +02:00
Georgi Gerganov	de51e3f3e3	sync : llama.cpp	2024-01-11 21:49:13 +02:00
Georgi Gerganov	98b3155750	sync : whisper.cpp (update whisper example + minor) (#613) ... ggml-ci	2023-11-17 10:00:11 +02:00
Georgi Gerganov	c2516858ba	ggml : sync latest llama.cpp	2023-06-19 20:35:08 +03:00
Georgi Gerganov	fe48e22fd6	ggml : new Q4 and Q5 quantization formats + backward ops ... sync llama.cpp - bump GGML_QNT_VERSION -> 1 - increase cwggml object overhead size from 256 to 512 in examples - drop Q4_2 support - tensor backend support CUDA	2023-05-14 15:18:34 +03:00
Georgi Gerganov	b9f8a53453	whisper : sync with latest	2023-05-02 21:28:21 +03:00
Georgi Gerganov	cf6815bfd2	ggml, whisper : sync whisper.cpp (GGML_FTYPE + Q5 WASM SIMD)	2023-04-30 19:03:35 +03:00
Georgi Gerganov	5dd92f421e	common : forgot to remove Q4_3 references	2023-04-29 10:30:56 +03:00
Georgi Gerganov	abea4b7609	ggml : sync llama.cpp (Q5_0 + Q5_1) + refactor examples quantization	2023-04-27 18:31:53 +03:00
Georgi Gerganov	bbb44f9668	examples : refactor quantization tools	2023-04-22 16:11:17 +03:00
Georgi Gerganov	e433b73f48	examples : utils -> common	2023-04-22 14:59:42 +03:00