7f162381ab
kvcache allocator ( #6901 )
...
* decode benchmark
* reject kvcache batch
* enable mha vulkan gemm out_elempack 1
2026-08-17 15:44:30 +08:00
127b414614
reshape support batch to/from dim ( #6784 )
2026-07-02 19:29:34 +08:00
f6f734f44d
vulkan int8 kernels ( #6751 )
...
* vulkan: add int8 kernels for core layers
Implement Vulkan int8 paths for convolution, convolutiondepthwise, innerproduct, and gemm with scalar fallback and integer dot product shader branches. Add goal.md and enable existing int8 unit tests for Vulkan coverage.
* enable int8 gpu benchmark
2026-06-17 17:39:49 +08:00
9c62afb90c
batch infrastructure ( #6656 )
...
* batch-aware record upload download
* cast and packing batch
2026-06-17 17:38:53 +08:00
6bc338e561
c-api / pyncnn expose more option setter getter ( #6489 )
2026-01-06 12:48:43 +08:00
171b9d1bba
use spdx license header, copyright Tencent ( #6152 )
2025-07-08 11:01:29 +08:00
0736c5b658
Fix c api allocator ( #4360 )
...
* add some c_api interfaces related to allocator setup.
* fix errors in allocator parameters in c_api.
* test c api allocator
Co-authored-by: zhangtongshe <yuyuyezi@vip.qq.com >
2022-11-21 11:03:46 +08:00
33e225f173
fix c api test
2022-01-21 22:41:07 +08:00
aa9753b2f0
detach mat from local blob allocator so net instance could be destroyed much earlier ( #3287 )
2021-10-16 10:22:10 +08:00
f1533667ff
fix test_c_api net instance destroyed earlier than blob destruction
2021-07-19 18:43:30 +08:00
b35b06be6d
reorg nhwc mode, code format
2020-12-29 18:57:48 +08:00
1040f40c8b
update c api for custom allocator datareader modelbin and layer registration, add cookie userdata to layer
2020-12-26 19:22:24 +08:00
2b7b92b726
update c api allocator
2020-12-25 23:22:31 +08:00
017440c1ca
update c api allocator
2020-12-25 23:10:49 +08:00
27e9795198
update c api
2020-12-25 20:05:39 +08:00
4114d333c9
low-level op api for C api
2020-12-25 15:13:10 +08:00
nihui