Member of Technical Staff @xai-org
Repositories
hebiao064/miles
Miles is an enterprise-facing reinforcement learning framework for LLM and VLM post-training, forked from and co-evolving with slime.
hebiao064/annotated_deep_learning_paper_implementations
🧑🏫 60+ Implementations/tutorials of deep learning papers with side-by-side notes 📝; including transformers (original, xl, switch, feedback, vit, ...), optimizers (adam, adabelief, sophia, ...), gans(cyclegan, stylegan2, ...), 🎮 reinforcement learning (ppo, dqn), capsnet, distillation, ... 🧠
hebiao064/verl
verl: Volcano Engine Reinforcement Learning for LLMs
hebiao064/hebiao064
Config files for my GitHub profile.
hebiao064/sglang
SGLang is a fast serving framework for large language models and vision language models.
hebiao064/batch_invariant_ops
hebiao064/lm-sys.github.io
hebiao064/slime
slime is a LLM post-training framework aiming at scaling RL.
hebiao064/torch_memory_saver
Allow torch tensor memory to be released and resumed later
hebiao064/nano-vllm
Nano vLLM
hebiao064/sgl-attn
Fast and memory-efficient exact attention
hebiao064/llm_interview_note
主要记录大语言大模型（LLMs） 算法（应用）工程师相关的知识及面试题
hebiao064/Awesome-ML-SYS-Tutorial
My learning notes/codes for ML SYS.
hebiao064/triton_puzzle
hebiao064/BetterChatGPT
An amazing UI for OpenAI's ChatGPT (Website + Windows + MacOS + Linux)
hebiao064/Liger-Kernel
Efficient Triton Kernels for LLM Training
hebiao064/flytekit
Extensible Python SDK for developing Flyte tasks and workflows. Simple to get started and learn and highly extensible.
hebiao064/ray
Ray is a unified framework for scaling AI and Python applications. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.
hebiao064/mighty-us-visa-bot
Mightest US Visa Bot of All Time
hebiao064/chatgpt_telegram_bot
hebiao064/rama
llama2 inference engine in Rust
hebiao064/flytesnacks
Flyte Documentation 📖
hebiao064/kaggle
hebiao064/Design-Pattern
hebiao064/ddia
《Designing Data-Intensive Application》DDIA中文翻译