Hello

Neural Magic at CVPR 2022

Are you heading to CVPR 2022 in New Orleans this June 19-23? So are we! And we’d love to meet you. Stop by booth #1223 and say hello. Who is Neural Magic? Passionate leaders with deep engineering backgrounds, Neural Magic has developed a sparsity-aware inference engine and open-source tools for maximizing the sparsity of neural… Read More Neural Magic at CVPR 2022

oBERT: Compound Sparsification Delivers Faster Accurate Models for NLP

GPU-Level Latency on CPUs With 10x Smaller Models using oBERT + DeepSparse The modern world is made up of constant communication happening through text. Think messaging apps, social networks, documentation and collaboration tools, or books. This communication generates enormous amounts of actionable data for companies that wish to use it to improve their users’ experiences.… Read More oBERT: Compound Sparsification Delivers Faster Accurate Models for NLP

Increasing Inference Performance with Sparsity and AMD Milan-X

In alignment with AMD's latest launch, Neural Magic is pushing CPU-based neural network execution to new heights. Using only software and SOTA sparsification research, Neural Magic achieves a 3x relative speedup of inference performance for sparse BERT NLP and ResNet-50 image classification models, with a nearly 20-25% boost attributed to the L3 cache increase from… Read More Increasing Inference Performance with Sparsity and AMD Milan-X

ResNet-50 on CPUs: Sparsifying for Better Performance on CPUs

In this post, we elaborate on how we measured, on commodity cloud hardware, the throughput and latency of five ResNet-50 v1 models optimized for CPU inference. By the end of the post, you should be able reproduce these benchmarks using tools available in the Neural Magic GitHub repo, ultimately achieving better performance for ResNet-50 on CPUs.… Read More ResNet-50 on CPUs: Sparsifying for Better Performance on CPUs

Accelerating Machine Learning Inference on CPU with VMware vSphere and Neural Magic

This blog was originally posted by Na Zhang on VMware's Office of the CTO Blog. You can see the original copy here. Increasingly large deep learning (DL) models require a significant amount of computing, memory, and energy, all of which become a bottleneck in real-time inference where resources are limited. In this post, we detail our… Read More Accelerating Machine Learning Inference on CPU with VMware vSphere and Neural Magic

Sparsify is Open Sourced - Try it Now

Today, we are very excited to provide you with early access to Sparsify, our automated model optimization tool! As deep learning models continue to grow in size, deploying and running them performantly and accurately has required significant investments in flops and system resources. Take GPT-3 for example, with over 175 billion parameters, it takes nearly… Read More Sparsify is Open Sourced - Try it Now

Product Release Notes

Release 0.1.0 for the Community! February 4, 2021 As of February 2021, our products have been renamed, most have been open sourced and their release notes can be be found in GitHub! Sparsify SparseML (formerly Neural Magic ML Tooling) SparseZoo (formerly Neural Magic Model Repo) DeepSparse Engine (formerly Neural Magic Inference Engine) Release 1.4.0 January… Read More Product Release Notes

Neural Magic at NeurIPS 2020

Are you attending this year’s virtual NeurIPS conference? The Neural Magic team would love to meet you.  Who is Neural Magic?  After years of research at MIT, our team concluded that throwing teraflops at dense models is not sustainable. So we’ve taken the best of known research on model compression (unstructured pruning and quantization, in… Read More Neural Magic at NeurIPS 2020

Neural Magic End-to-End Demo Videos

Neural Magic delivers best-in-class deep learning performance on commodity CPUs. We do this via: Model optimization techniques like pruning and quantization Smart algorithms that utilize CPU memory more effectively. To help visualize the power of Neural Magic, we recorded three short end-to-end video guides on how to install our software, prepare and run a model… Read More Neural Magic End-to-End Demo Videos

Part 3: Gradual Magnitude Pruning (GMP) Hyperparameters

TL;DR: To facilitate the GMP process when pruning a network, several hyperparameters must be defined. These include general hyperparameters such as learning rate, pruning update frequency, and pruning schedule function in addition to the sparsity per layer. All hyperparameters affect end level recovery, loss, and performance. Reading time: 5 minutes, 5 seconds Welcome to Part… Read More Part 3: Gradual Magnitude Pruning (GMP) Hyperparameters