SparseTIR: Sparse Tensor Compiler for Deep Learning

🤗Transformers: State-of-the-art Natural Language Processing for Pytorch and TensorFlow 2.0.

Paella: Low-latency Model Serving with Virtualized GPU Scheduling

BERT based pretrained model using SQuAD 2.0 Dataset for Question-Answering

A Vectorized N:M Format for Unleashing the Power of Sparse Tensor Cores

OSDI 2023 Welder, deeplearning compiler

A retargetable MLIR-based machine learning compiler and runtime toolkit.

A flexible and efficient deep neural network (DNN) compiler that generates high-performance executable from a DNN model description.

An implementation of the BERT model and its related downstream tasks based on the PyTorch framework

compiler learning resources collect.

In this repository, I will publish my notes for GaTech's Advanced Operating Systems course (CS6210).

The Torch-MLIR project aims to provide first class support from the PyTorch ecosystem to the MLIR ecosystem.

C++那些事

A Kubernetes mutating webhook server that implements sidecar injection

elastic-gpu-scheduler is a Kubernetes scheduler extender for GPU resources scheduling.

heterogeneity-aware-lowering-and-optimization

elastic-gpu-agent is a Kubernetes device plugin for GPU resources allocation on node.

My resume

Run your deep learning workloads on Kubernetes more easily and efficiently.

NVIDIA container runtime library

Plots seismic, sorta