Stars
Tools for merging pretrained large language models.
MiniMax-M1, the world's first open-weight, large-scale hybrid-attention reasoning model.
🚀 Efficient implementations of state-of-the-art linear attention models
Repo for "LoLCATs: On Low-Rank Linearizing of Large Language Models"
M1: Towards Scalable Test-Time Compute with Mamba Reasoning Models
verl: Volcano Engine Reinforcement Learning for LLMs
[NeurIPS'24 Spotlight, ICLR'25, ICML'25] To speed up Long-context LLMs' inference, approximate and dynamic sparse calculate the attention, which reduces inference latency by up to 10x for pre-filli…
Code for paper: [ICLR2025 Oral] FlexPrefill: A Context-Aware Sparse Attention Mechanism for Efficient Long-Sequence Inference
Fast and memory-efficient exact attention
Function Vectors in Large Language Models (ICLR 2024)
A library for mechanistic interpretability of GPT-style language models
[ICLR 2025] Official PyTorch Implementation of Gated Delta Networks: Improving Mamba2 with Delta Rule
VeOmni: Scaling any Modality Model Training to any Accelerators with PyTorch native Training Framework
Efficient Triton Kernels for LLM Training
FlashMLA: Efficient MLA decoding kernels
Development repository for the Triton language and compiler
MoBA: Mixture of Block Attention for Long-Context LLMs
A sparse attention kernel supporting mix sparse patterns
A Flexible Framework for Experiencing Cutting-edge LLM Inference Optimizations
[ICLR 2025] Systematic Outliers in Large Language Models.
Unified KV Cache Compression Methods for Auto-Regressive Models
Awesome diffusion Video-to-Video (V2V). A collection of paper on diffusion model-based video editing, aka. video-to-video (V2V) translation. And a video editing benchmark code.
[ICML 2024] Quest: Query-Aware Sparsity for Efficient Long-Context LLM Inference
Enjoy the magic of Diffusion models!
This repository collects all relevant resources about interpretability in LLMs