google / tunixLinks
A Lightweight LLM Post-Training Library
☆2,092Updated this week
Alternatives and similar repositories for tunix
Users that are interested in tunix are comparing it to the libraries listed below
Sorting:
- Post-training with Tinker☆2,699Updated this week
- Build RL environments for LLM training☆568Updated this week
- An interface library for RL post training with environments.☆973Updated this week
- Renderer for the harmony response format to be used with gpt-oss☆4,124Updated 3 weeks ago
- PyTorch-native post-training at scale☆584Updated this week
- Scalable toolkit for efficient model reinforcement☆1,210Updated this week
- Async RL Training at Scale☆976Updated this week
- Supercharge Your LLM with the Fastest KV Cache Layer☆6,657Updated this week
- A compact implementation of SGLang, designed to demystify the complexities of modern LLM serving systems.☆2,830Updated this week
- Our library for RL environments + evals☆3,699Updated this week
- A framework for efficient model inference with omni-modality models☆1,977Updated this week
- ☆945Updated 2 months ago
- A lightweight, local-first, and 🆓 experiment tracking library from Hugging Face 🤗☆1,191Updated this week
- ☆716Updated last month
- On the Theoretical Limitations of Embedding-Based Retrieval☆618Updated 3 months ago
- cuTile is a programming model for writing parallel kernels for NVIDIA GPUs☆1,722Updated 2 weeks ago
- ☆1,257Updated last month
- Embedding Atlas is a tool that provides interactive visualizations for large embeddings. It allows you to visualize, cross-filter, and se…☆4,505Updated 2 weeks ago
- Atropos is a Language Model Reinforcement Learning Environments framework for collecting and evaluating LLM trajectories through diverse …☆782Updated this week
- PyTorch Single Controller☆939Updated this week
- bloom - evaluate any behavior immediately 🌸🌱☆1,027Updated this week
- Render any git repo into a single static HTML page for humans or LLMs☆1,990Updated 4 months ago
- Self-Adapting Language Models☆1,637Updated 5 months ago
- The NVIDIA NeMo Agent toolkit is an open-source library for efficiently connecting and optimizing teams of AI agents.☆1,671Updated this week
- Checkpoint-engine is a simple middleware to update model weights in LLM inference engines☆885Updated this week
- Research code artifacts for Code World Model (CWM) including inference tools, reproducibility, and documentation.☆792Updated 2 weeks ago
- A benchmark for LLMs on complicated tasks in the terminal☆1,284Updated last week
- The missing tiktoken training code☆162Updated this week
- FlexAttention based, minimal vllm-style inference engine for fast Gemma 2 inference.☆329Updated 2 months ago
- dLLM: Simple Diffusion Language Modeling☆1,541Updated this week