Stars
Ray is an AI compute engine. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.
SGLang is a fast serving framework for large language models and vision language models.
An open-source C++ library developed and used at Facebook.
GEAR: An Efficient KV Cache Compression Recipefor Near-Lossless Generative Inference of LLM
😎 Awesome lists about all kinds of interesting topics
This tool provides an efficient implementation of the continuous bag-of-words and skip-gram architectures for computing vector representations of words. These representations can be subsequently us…
Flash Attention in ~100 lines of CUDA (forward pass only)
A natural language interface for computers
[NeurIPS 24] MoE Jetpack: From Dense Checkpoints to Adaptive Mixture of Experts for Vision Tasks
Tensors and Dynamic neural networks in Python with strong GPU acceleration
Zero Bubble Pipeline Parallelism
mfdj2002 / classifier-free-diffusion-guidance-Pytorch
Forked from coderpiaobozhe/classifier-free-diffusion-guidance-Pytorcha simple unofficial implementation of classifier-free diffusion guidance
Lifelong Learning with Dynamically Expandable Networks, ICLR 2018
Concept Bottleneck Models, ICML 2020
Large Language-and-Vision Assistant for Biomedicine, built towards multimodal GPT-4 level capabilities.
a simple unofficial implementation of classifier-free diffusion guidance
Training and serving large-scale neural networks with auto parallelization.
The official implementation of Self-Play Fine-Tuning (SPIN)
[COLM'24] "Deductive Beam Search: Decoding Deducible Rationale for Chain-of-Thought Reasoning"
Zero-Shot Chain-of-Thought Reasoning Guided by Evolutionary Algorithms in Large Language Models
Diffusion Classifier leverages pretrained diffusion models to perform zero-shot classification without additional training
An easy to use, user-friendly and efficient code for extracting OpenAI CLIP (Global/Grid) features from image and text respectively.
Code for Finetune like you pretrain: Improved finetuning of zero-shot vision models
An open source implementation of CLIP.
CLIP (Contrastive Language-Image Pretraining), Predict the most relevant text snippet given an image