- ๐ญ Iโm currently exploring AI Infrastructure, with a special focus on AI compilers and LLM inference acceleration.
- ๐ฑ Iโm diving into CUTLASS, Triton, IREE, vLLM, and other AI compilers or inference engines.
- ๐ฏ Iโm looking to collaborate on AI compiler development or hardware-specific LLM inference acceleration.
- ๐ I regularly write articles on micropuma.github.io
- ๐ซ How to reach me leondou@bupt.edu.cn
Postgraduate student at Beijing University of Posts and Telecommunications
-
12:19
(UTC +08:00) - micropuma.github.io
Highlights
- Pro
Pinned Loading
-
-
-
BladeDISC-dly
BladeDISC-dly PublicForked from alibaba/BladeDISC
BladeDISC is an end-to-end DynamIc Shape Compiler project for machine learning workloads.
C++
-
-
vllm-dly
vllm-dly PublicForked from vllm-project/vllm
A high-throughput and memory-efficient inference and serving engine for LLMs
Python
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.