Starred repositories
1092
results
for source starred repositories
Clear filter
A low-latency & high-throughput serving engine for LLMs
[OSDI'24] Serving LLM-based Applications Efficiently with Semantic Variable
Supercharge Your LLM with the Fastest KV Cache Layer
Code for paper "Confidence v.s. Critique: A Decomposition of Self-Correction Capability for LLMs"
"DeepTutor: AI-Powered Personalized Learning Assistant"
Accurate traffic splitting (multipath routing) technique for software switch (implemented on Open vSwitch)
REPETITA: Repeatable Experiments for Performance Evaluation of Traffic-Engineering Algorithms
A scalable and accurate probabilistic network configuration analyzer verifying network properties in the face of random failures.
An accurate performance prediction framework for on-NIC network functions
本科华五，曾赴美qs50读博，某兄弟院校副教授，校园门卫亭女性主理人，为防止炸号的备份平台，是本人。
SGLang is a high-performance serving framework for large language models and multimodal models.
[NSDI'25] The library of Network Decision Diagram based on JDD.
"Paper2Slides: From Paper to Presentation in One Click"
Python client for Batfish: https://github.com/batfish/batfish
Introduction to Machine Learning Systems
Experiments for distributed optimization algorithms
Pytorch implementation of preconditioned stochastic gradient descent (Kron and affine preconditioner, low-rank approximation preconditioner and more)
Packet-level simulation code to model Opera and other networks from the 2020 NSDI paper "Expanding across time to deliver bandwidth efficieny and low latency"
This repository contains the artifact for the Middleware'24 paper: "PvCC: A vCPU Scheduling Policy for DPDK-applied Systems at Multi-Tenant Edge Data Centers"
[ICLR 2022] The implementation for the paper "Equivariant Graph Mechanics Networks with Constraints".
Customize, control, and enhance LLM generation with logits processors, featuring visualization capabilities to inspect and understand state transitions