Stars
FlashInfer: Kernel Library for LLM Serving
A general-purpose programmatic animation tool
ASCII generator (image to text, image to image, video to video)
D2 is a modern diagram scripting language that turns text to diagrams.
Repository for Meta Chameleon, a mixed-modal early-fusion foundation model from FAIR.
📚A curated list of Awesome LLM/VLM Inference Papers with Codes: Flash-Attention, Paged-Attention, WINT8/4, Parallelism, etc.🎉
A generative speech model for daily dialogue.
Fast and memory-efficient exact attention
Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities
Scalable toolkit for efficient model alignment
Tile primitives for speedy kernels
A library for accelerating Transformer models on NVIDIA GPUs, including using 8-bit and 4-bit floating point (FP8 and FP4) precision on Hopper, Ada and Blackwell GPUs, to provide better performance…
LMDeploy is a toolkit for compressing, deploying, and serving LLMs.
CV-CUDA™ is an open-source, GPU accelerated library for cloud-scale image processing and computer vision.
[ICML 2023] SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models
ChatGLM-6B: An Open Bilingual Dialogue Language Model | 开源双语对话语言模型
Accessible large language models via k-bit quantization for PyTorch.
Transformer related optimization, including BERT, GPT
The road to hack SysML and become an system expert
X-modaler is a versatile and high-performance codebase for cross-modal analytics(e.g., image captioning, video captioning, vision-language pre-training, visual question answering, visual commonsens…
CLIP (Contrastive Language-Image Pretraining), Predict the most relevant text snippet given an image
Code for "Discovering Symbolic Models from Deep Learning with Inductive Biases"
An index of algorithms for learning causality with data
Repository with code and slides for a tutorial on causal inference.