-
Baidu
Block or Report
Block or report Xreki
Report abuse
Contact GitHub support about this user’s behavior. Learn more about reporting abuse.
Report abusePopular repositories
-
-
-
-
CNNdroid Public
Forked from ENCP/CNNdroid
Open Source Library for GPU-Accelerated Execution of Trained Deep Convolutional Neural Networks on Android
Java 1
-
marp Public
Forked from yhatt/marp
Markdown presentation writer, powered by Electron.
CoffeeScript 1
-
468 contributions in the last year
Less
More
Activity overview
Contributed to
PaddlePaddle/Paddle,
PaddlePaddle/benchmark,
PaddlePaddle/CINN
and 5 other
repositories
Contribution activity
April 2022
Created 4 commits in 1 repository
Created a pull request in PaddlePaddle/Paddle that received 2 comments
[Cherry-pick 2.3] Autotune the workspace and kernel choosing of conv
+1,178
−839
•
2
comments
Opened 3 other pull requests in 2 repositories
PaddlePaddle/Paddle
2
merged
PaddlePaddle/CINN
1
open
Reviewed 14 pull requests in 3 repositories
PaddlePaddle/Paddle
10 pull requests
- Dynamic graph support to Automatic SParsity.
- [Cherry-Pick]Move pass optimizations into CINN. (#42047)
- Move pass optimizations into CINN.
- [cherry-pick] Implement Amp Layout AutoTune(41884)
- Implement Amp Layout AutoTune
- Add float16 to fake quantize/dequantize OP
- Change cuDNN Conv kernel for auto tune feature
- Add yaml for deformable_conv and deformable_conv_v1 OPs
- Implement AutoTuneStatus class for Kernel Auto Tune
- Add nms op and batched_nms api

