每个人都能看懂的大模型知识分享，LLMs春/秋招大模型面试前必看，让你和面试官侃侃而谈

Protobuf VS FlatBuffers VS Json序列化比较

Agent framework and applications built upon Qwen>=3.0, featuring Function Calling, MCP, Code Interpreter, RAG, Chrome extension, etc.

FB (Facebook) + GEMM (General Matrix-Matrix Multiplication) - https://code.fb.com/ml-applications/fbgemm/

Rust bindings for the C++ api of PyTorch.

A Gym for Agentic LLMs

HuggingFace conversion and training library for Megatron-based models

Sky-T1: Train your own O1 preview model within $450

Example models using DeepSpeed

group project of polyu comp5517, job finding assistant via LLM

PyTorch implementation of Constrained Reinforcement Learning for Soft Actor Critic Algorithm

AuctionGym is a simulation environment that enables reproducible evaluation of bandit and reinforcement learning methods for online advertising auctions.

Rust bindings for XGBoost.

A GPU-accelerated graph learning library for PyTorch, facilitating the scaling of GNN training and inference.

📚LeetCUDA: Modern CUDA Learn Notes with PyTorch for Beginners🐑, 200+ CUDA Kernels, Tensor Cores, HGEMM, FA-2 MMA.🎉

A Survey of Reinforcement Learning for Large Reasoning Models

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

Study of MCP course

The simplest, fastest repository for training/finetuning medium-sized GPTs.

adds Sequence Parallelism into LLaMA-Factory

A library that provides an embeddable, persistent key-value store for fast storage.

Efficient triton implementation of Native Sparse Attention.

《AI 研发提效研究：自己动手训练 LoRA》，包含 Llama （Alpaca LoRA）模型、ChatGLM （ChatGLM Tuning）相关 Lora 的训练。训练内容：用户故事生成、测试代码生成、代码辅助生成、文本转 SQL、文本生成代码……

code for "Diffusion Forcing: Next-token Prediction Meets Full-Sequence Diffusion"

Retrieval with Learned Similarities

Robust recipes to align language models with human and AI preferences