8 Commits

Author	SHA1	Message	Date
nihui	171b9d1bba	use spdx license header, copyright Tencent (#6152)	2025-07-08 11:01:29 +08:00
nihui	4a70be45ed	fix requantize pack4to8 (#5893)	2025-02-07 10:46:32 +08:00
nihui	956bccd295	restrict one dim requantize scale bias size (#5888)	2025-02-05 10:57:41 +08:00
nihui	556b79ce4d	create layer decoupled (#5258) ... * create layer decoupled * no more virtual public * allow build test with shared library * decouple cpu vulkan * drop old scripts	2024-01-05 14:08:15 +08:00
nihui	6941ec8fc9	arm neon optimization for general packed convolution (#3426)	2021-12-22 12:18:17 +08:00
nihui	c6cda8d07c	arm neon optimization for requantize leakyrelu (#3144) ... * arm neon optimization for requantize leakyrelu * add missing changes * Update test_requantize.cpp * more test coverage	2021-08-06 13:31:32 +08:00
nihuini	934a1a8e32	test flatten packing padding int8	2021-06-17 19:42:45 +08:00
nihui	5fe75f19ef	architecture changes for int8 packing (#2771) ... * quantize and dequantize tests * unify activation and usability function * drop NCNN_REQUANT cmake option, test dequantize requantize pack8, fix webassembly build * benchmark use requantize int8 model	2021-03-27 18:49:13 +08:00