Pretty good call graphs for dynamic languages

verl: Volcano Engine Reinforcement Learning for LLMs

技术面试最后反问面试官的话

Systems of Reinforcement Learning

A scalable generative AI framework built for researchers and developers working on Large Language Models, Multimodal, and Speech AI (Automatic Speech Recognition and Text-to-Speech)

A high-throughput and memory-efficient inference and serving engine for LLMs

Miles is an enterprise-facing reinforcement learning framework for LLM and VLM post-training, forked from and co-evolving with slime.

slime is an LLM post-training framework for RL Scaling.

Repository used to store the GKE AI Labs content for "Tutorials and Examples" section

Amazons implementation example

Amazon Chess Program for Data Structures course design.

北京大学计算机基础能力手册

Optimized primitives for collective multi-GPU communication

Verified Rust for low-level systems code

For reproducing RPC transient errors ...

Codes & examples for "CUDA - From Correctness to Performance"

Domain-specific language designed to streamline the development of high-performance GPU/CPU/Accelerators kernels

A curated reading list for machine learning reliability research and practice

Nano vLLM

A course of learning LLM inference serving on Apple Silicon for systems engineers: build a tiny vLLM + Qwen.

Collections of SysY language testcases.

TiDB - the open-source, cloud-native, distributed SQL database designed for modern applications.

📰 Must-read papers and blogs on Speculative Decoding ⚡️

SGLang is a high-performance serving framework for large language models and multimodal models.

Disaggregated serving system for Large Language Models (LLMs).

A Datacenter Scale Distributed Inference Serving Framework

FlashInfer: Kernel Library for LLM Serving

Toolkit for linearizing PDFs for LLM datasets/training

PyTorch library for cost-effective, fast and easy serving of MoE models.