- 👋 Hi, I’m @yiakwy-xpu-ml-framework-team
- 👀 I’m interested in accelerating the word through algorithms, chips and intelligence. (compiler/transpiler, c++ ops development/optimization for critical path of overall performance and python bindings for HPC application.)
- 🌱 I’m currently working on core framework infrastracture and AI compilier technologies.
- 📫 Please drop me a message through yiak.wy@gmail.com
I may be slow to respond.
Hi I am LEI WANG. AI / LLM Architect, previously working in Graphcore IPU compiler team.
-
independent contributor @ HPC Users Alliance
- United States
-
13:19
(UTC -12:00) - https://yiakwy.github.io/
- in/lei-wang-1722a28a
- @yiakwy2023
- https://mp.weixin.qq.com/s/AVujFosiC15ZmSRvByYcRQ
- https://mp.weixin.qq.com/s/13NKhY3GccjU9Emz-cRSHQ
Highlights
- Pro
Popular repositories Loading
-
-
NV_grouped_gemm
NV_grouped_gemm PublicForked from fanshiqing/grouped_gemm
PyTorch bindings for CUTLASS grouped GEMM for MoE.
Cuda 7
-
Toolkit-remote-pdb-for-pytorch-distributed
Toolkit-remote-pdb-for-pytorch-distributed PublicDebugging torch distributed program
Python 7
-
-
GC-OXFORD-CVPR2021-gbp-poplar
GC-OXFORD-CVPR2021-gbp-poplar PublicForked from joeaortiz/gbp-poplar
Poplar implementation of "Bundle Adjustment on a Graph Processor" (CVPR 2020)
C++ 2
Something went wrong, please refresh the page to try again.
If the problem persists, check the GitHub status page or contact support.
If the problem persists, check the GitHub status page or contact support.



