a collection of mini-games on mechanistic interpretability

NVIDIA Linux open GPU with P2P support

My learning notes for ML SYS.

[EMNLP 2024] TraveLER: A Modular Multi-LMM Agent Framework for Video Question-Answering

[ICLR 2025] Palu: Compressing KV-Cache with Low-Rank Projection

Helpful tools and examples for working with flex-attention

The code of our paper "InfLLM: Unveiling the Intrinsic Capacity of LLMs for Understanding Extremely Long Sequences with Training-Free Memory"

[ICML'24] Data and code for our paper "Training-Free Long-Context Scaling of Large Language Models"

[ICLR'25] Data and code for our paper "Why Does the Effective Context Length of LLMs Fall Short?"

Sudoku solving in python packaging

3D plotting and mesh analysis through a streamlined interface for the Visualization Toolkit (VTK)

Code for visualizing the loss landscape of neural nets

Materials for learning SGLang

[ECCV 2024 Oral] Code for paper: An Image is Worth 1/2 Tokens After Layer 2: Plug-and-Play Inference Acceleration for Large Vision-Language Models

[ICLR 2024] Efficient Streaming Language Models with Attention Sinks

[NeurIPS'23] H2O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models.

Efficient Triton Kernels for LLM Training

Streamlit Component to quickly create Interactive Flow Diagrams using React Flow

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

Accompanying code for the paper Coprocessor Actor Critic: A Model-Based Reinforcement Learning Approach For Adaptive Brain Stimulation.

[ICML 2024] LLMCompiler: An LLM Compiler for Parallel Function Calling

Everything you want to know about Google Cloud TPU

[ACM MM 2023] Official implementation of "Hierarchical Masked 3D Diffusion Model for Video Outpainting"

Animate Anyone: Consistent and Controllable Image-to-Video Synthesis for Character Animation

[CVPR 2024] Official repository for "MagicAnimate: Temporally Consistent Human Image Animation using Diffusion Model"

A markup-based typesetting system that is powerful and easy to learn.

[NeurIPS 2023] Self-Chained Image-Language Model for Video Localization and Question Answering