#
Starred repositories
137
stars
written in Python
Clear filter
State-of-the-art deep learning model for analyzing sentiment, emotion, sarcasm etc.
Reference implementations of MLPerf® inference benchmarks
[NeurIPS 2025] MMaDA - Open-Sourced Multimodal Large Diffusion Language Models
source code from the book Genetic Algorithms with Python by Clinton Sheppard
Corruption and Perturbation Robustness (ICLR 2019)
Simple reference implementation of GraphSAGE.
Multi-Agent Resource Optimization (MARO) platform is an instance of Reinforcement Learning as a Service (RaaS) for real-world resource optimization problems.
a pytorch lib with state-of-the-art architectures, pretrained models and real-time updated results
ACNet: Strengthening the Kernel Skeletons for Powerful CNN via Asymmetric Convolution Blocks
[CVPR'19 Oral] Deeper and Wider Siamese Networks for Real-Time Visual Tracking
A Genetic Algorithm Framework in Python (not for production level)
Kubernetes-native Deep Learning Framework
[CVPR 2024 Highlight] DistriFusion: Distributed Parallel Inference for High-Resolution Diffusion Models
A PyTorch implementation of GraphSAGE. This package contains a PyTorch implementation of GraphSAGE.
[COLM 2024] LoraHub: Efficient Cross-Task Generalization via Dynamic LoRA Composition
Implementation of MEGABYTE, Predicting Million-byte Sequences with Multiscale Transformers, in Pytorch
A command-line tool for launching Apache Spark clusters.
A general and accurate MACs / FLOPs profiler for PyTorch models
a distributed Hyperband implementation on Steroids
Chatbot Arena meets multi-modality! Multi-Modality Arena allows you to benchmark vision-language models side-by-side while providing images as inputs. Supports MiniGPT-4, LLaMA-Adapter V2, LLaVA, B…
PyTorch Implementation of DARTS: Differentiable Architecture Search
Resource-adaptive cluster scheduler for deep learning training.
Python Single Object Tracking Evaluation
solution to "syscall.Mprotect panic: permission denied" on macOS Catalina 10.15.x
A ChatGPT(GPT-3.5) & GPT-4 Workload Trace to Optimize LLM Serving Systems