Ruihang Lai

Enable everyone to develop, optimize and deploy AI models natively on everyone's devices.

Open deep learning compiler stack for cpu, gpu and specialized accelerators

Bringing large-language models and chat to web browsers. Everything runs inside the browser with no server support.

SparseTIR: Sparse Tensor Compiler for Deep Learning

No description.

No description.

🔪Mx-Star Compiler Project

Project for SJTU CS158 Data Structure(Honor) Spring 2020

Course Project of CS392, Database Management System, SJTU, 2021 Spring

Project of MS110 - Computer System (2) - Spring 2020 - SJTU

DHT assignment repository for PPCA 2020, SJTU

🖥️A CPU in Verilog that implements the RISC-V 32b integer base user-level real-mode ISA.

TensorRT LLM Benchmark Configuration

🕹️A simple analytical engine emulator used for course "Great Ideas in Computer Science"

Minimal BASIC Interpreter

A simple RISC-V simulator

🤖Course repository for SJTU CS420.

TVM FFI

DeepGEMM: clean and efficient FP8 GEMM kernels with fine-grained scaling

SGLang is a fast serving framework for large language models and vision language models.

A standalone GEMM kernel for fp16 activation and quantized weight, extracted from FasterTransformer

Project website of FlashInfer project

CSD Blog

Development repository for the Triton language and compiler

FlashInfer: Kernel Library for LLM Serving

Bringing stable diffusion models to web browsers. Everything runs inside the browser with no server support.

Temp repo for prototyping relax(relay next), the effort will be upstreamed. We use the wiki pages on this repo to host design docs.

No description.

No description.

No description.

No description.

A System for Train Ticket

Deep Learning and Its Applications - 2020 Fall - SJTU

CS217 - Algorithm Design and Analysis - Spring 2020 - SJTU

class Matrix

A C++ STL priority queue

A C++ STL map

A C++ STL deque

🖧Distributed Hash Table with Chord Protocol (and Kademlia)