Jifeng Wu's Personal Website

This project explored how to lower machine-learning-oriented IR into low-level compiler IR by building a small MLIR-based compiler. The tool reads StableHLO MLIR, applies a sequence of lowering and cl

2026-04 Financial Statement

Using MLIR as a C++ Library with a Relocatable Install

Docker and Podman Containers as Lightweight VMs for Interactive Work

A summary of Jie Liu's B-exam on sparse tensor computation, covering sparse format conversion, asynchronous GPU execution, and the design of high-performance BCSR/WCSR SpMM kernels.

A critique of RFSeek, arguing that provenance-linked RFC visualization is valuable but that the underlying methodology remains closer to a retrieval-augmented prompting pipeline than to an agentic, ve

A short overview of Kleene algebra and how NetKAT and StacKAT use it to model network behavior.

《经济学的思维方式》第一章读书摘录

A bullet-point summary of a group discussion on AI coding, hiring, interviews, and AI-native engineering workflows.

A mental model for the difference between PyTorch + CUDA and the XLA + TPU execution style.