#
Starred repositories
137
stars
written in Python
Clear filter
SenseTime Research platform for single object tracking, implementing algorithms like SiamRPN and SiamMask.
Differentiable architecture search for convolutional and recurrent networks
A terminal application to view, tail, merge, and search log files (plus JSONL).
SWE-bench: Can Language Models Resolve Real-world Github Issues?
OpenMMLab Pre-training Toolbox and Benchmark
LightLLM is a Python-based LLM (Large Language Model) inference and serving framework, notable for its lightweight design, easy scalability, and high-speed performance.
A high performance and generic framework for distributed DNN training
VILA is a family of state-of-the-art vision language models (VLMs) for diverse multimodal AI tasks across the edge, data center, and cloud.
Representation learning on large graphs using stochastic graph convolutions.
Multi-LoRA inference server that scales to 1000s of fine-tuned LLMs
PyTorch extensions for high performance and large scale training.
Training and serving large-scale neural networks with auto parallelization.
A web app for ranking computer science departments according to their research output in selective venues, and for finding active faculty across a wide range of areas.
A Pythonic framework to simplify AI service building
PyTorch implementation of "Efficient Neural Architecture Search via Parameters Sharing"
Code for "Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks"
Automated Deep Learning: Neural Architecture Search Is Not the End (a curated list of AutoDL resources and an in-depth analysis)
MII makes low-latency and high-throughput inference possible, powered by DeepSpeed.
[ICLR 2020] Once for All: Train One Network and Specialize it for Efficient Deployment
S-LoRA: Serving Thousands of Concurrent LoRA Adapters
Reference implementations of MLPerf® training benchmarks
pip install antialiased-cnns to improve stability and accuracy