#
Lists (20)
Starred repositories
Curated collection of papers in machine learning systems
AIInfra（AI 基础设施）指AI系统从底层芯片等硬件，到上层软件栈支持AI大模型训练和推理。
YOLOv3 in PyTorch > ONNX > CoreML > TFLite
Deep Residual Learning for Image Recognition
Models and examples built with TensorFlow
Disaggregated serving system for Large Language Models (LLMs).
Summary of some awesome work for optimizing LLM inference
A low-latency & high-throughput serving engine for LLMs
The Course Project of CS7304H Statistical Learning in SJTU
A collection of Twitter's anonymized production cache traces.
A collection of pre-trained, state-of-the-art models in the ONNX format
PDF references add-on for Zotero.
Automatic tuning for ML model deployment on Kubernetes
Proteus: A High-Throughput Inference-Serving System with Accuracy Scaling
SmartFD: Efficient and Scalable Functional Dependency Discovery on Distributed Data-Parallel Platforms