TE
TechEcho
Home24h TopNewestBestAskShowJobs
GitHubTwitter
Home

TechEcho

A tech news platform built with Next.js, providing global tech news and discussions.

GitHubTwitter

Home

HomeNewestBestAskShowJobs

Resources

HackerNews APIOriginal HackerNewsNext.js

© 2025 TechEcho. All rights reserved.

Deploying Transformers on the Apple Neural Engine

121 pointsby vletalalmost 3 years ago

5 comments

axg11almost 3 years ago
Apple is still behind the rest of FAANG in terms of publishing ML research, but they&#x27;ve taken the lead in terms of real world impact of ML. If you go back a couple of years the general consensus was that Apple is very far behind and lacks any credible machine learning groups. As with most of their products, they waited for the technology to mature (a bit) and then made magical experiences from it.<p>Some examples:<p>- On-device semantic image search<p>- Text highlighting (images and videos)<p>- FaceID<p>- Computational photography, depth mapping (sensor fusion)<p>- Background removal (iOS 16)<p>- Activity detection (Apple Watch)<p>Siri is still far behind vs. Alexa and Google Assistant, but for every other ML&#x2F;AI application I&#x27;d argue that Apple has the smoothest experience. This should be a lesson for others building ML-powered products. You don&#x27;t need to use the best, state of the art models to compete. You can compete on the overall experience.<p>Sharing details and publications doesn&#x27;t seem to be a core part of Apple&#x27;s culture, so I&#x27;m glad they&#x27;re going out of their way to publish more details like this article. Their push to optimize ML inference for on-device rather than cloud is going to have the biggest impact on consumer experience. I&#x27;m fairly sure this is part of their AR&#x2F;VR strategy too. Low-latency local machine learning that powers magical experiences.
评论 #31668226 未加载
评论 #31668715 未加载
评论 #31667949 未加载
评论 #31667801 未加载
评论 #31667645 未加载
评论 #31667601 未加载
评论 #31667846 未加载
评论 #31668390 未加载
评论 #31669838 未加载
评论 #31670105 未加载
评论 #31674815 未加载
评论 #31673483 未加载
评论 #31674565 未加载
评论 #31667936 未加载
pavlovalmost 3 years ago
Recently I bought a Mac Studio and wanted to experiment with Apple&#x27;s GPU-accelerated ML API under the Metal Performance Shaders framework.<p>I downloaded a sample code project from WWDC 2019: <a href="https:&#x2F;&#x2F;developer.apple.com&#x2F;documentation&#x2F;metalperformanceshaders&#x2F;training_a_neural_network_with_metal_performance_shaders" rel="nofollow">https:&#x2F;&#x2F;developer.apple.com&#x2F;documentation&#x2F;metalperformancesh...</a><p>It didn&#x27;t build on latest Xcode on the Mac Studio. I&#x27;m experienced with Cocoa and Apple&#x27;s APIs, but couldn&#x27;t fix the problem in 30 minutes of poking around.<p>Then I found another sample code project from WWDC 2020 which is apparently using a similarly named but different API for the same purpose: <a href="https:&#x2F;&#x2F;developer.apple.com&#x2F;documentation&#x2F;metalperformanceshadersgraph&#x2F;training_a_neural_network_using_mps_graph" rel="nofollow">https:&#x2F;&#x2F;developer.apple.com&#x2F;documentation&#x2F;metalperformancesh...</a><p>This one looked promising, but failed with a runtime assertion and I was unable to figure it out.<p>At this point I wish Apple spent more effort on making their existing frameworks usable. If the only available sample code doesn&#x27;t even work on a brand new Mac, the API isn&#x27;t going to be used by third parties.
评论 #31671881 未加载
评论 #31673576 未加载
vletalalmost 3 years ago
I wonder how approachable it would be to optimise a custom model for ANE. According to the code examples at the bottom, the current implementation seems to be a custom model, so no generic solution.<p>Anyway, it seems that we are at dawn of deploying mode cool models which formerly required cloud computation to the hands of the users. Really cool!<p>Are we going to see more federated learning being pushed to user devices or is it a dead branch only useful for a few use cases?
评论 #31702897 未加载
navanchauhanalmost 3 years ago
First party support for models hosted on HuggingFace for optimisation&#x2F;conversion! Pretty stoked about playing with it
ameliusalmost 3 years ago
Suprised to find out that there is not a simple abstraction layer that makes it the same across all platforms.
评论 #31670895 未加载
评论 #31667603 未加载