提交 · 80e2464f8cc7b96ddc6f5478b18afb49f3694e94 · PaddlePaddle / Paddle-Lite

13 12月, 2019 1 次提交
- H
  [LITE][NPU][XPU] Refine subgraph pass, and support NPU/XPU model generation at... · d5434aa2
  由 hong19860320 提交于 12月 13, 2019
```
[LITE][NPU][XPU] Refine subgraph pass, and support NPU/XPU model generation at execution time (#2576)
```
  d5434aa2
14 11月, 2019 1 次提交
- H
  
  [LITE][NPU] Upgrade HiAI DDK from 300 to 310 (#2423) · c1837d76
  由 hong19860320 提交于 11月 14, 2019
  
  c1837d76
08 11月, 2019 1 次提交

[LITE][NPU] Add fusion_elementwise_add_activation bridge, remove the... · aacba6f5

由 hong19860320 提交于 11月 08, 2019

[LITE][NPU] Add fusion_elementwise_add_activation bridge, remove the limitation of the dimensions of input tensors in the graph compute kernel, and refine log message (#2395)

test=develop

aacba6f5

30 10月, 2019 1 次提交
- H
  
  [LITE][NPU] Use FullConnection op to solve the compatibility between Kirin 810 and 990 (#2283) · f3e5d3e5
  由 hong19860320 提交于 10月 30, 2019
  
  f3e5d3e5
29 10月, 2019 1 次提交
- H
  [LITE][NPU] Add supporting for Huawei offical DDK (#2262) · dc2b853e
  由 hong19860320 提交于 10月 29, 2019
```
* Add supporting for Huawei offical DDK
* Fix the param of graph op in NPU graph computing kernel
```
  dc2b853e