Intel Patents Parallel Huffman Decoding to Compress LLM Weights on GPU
Running a large language model on a GPU requires moving enormous amounts of weight data around — and that bandwidth cost is…
Every newly published filing from Apple, Google, Microsoft, Meta, Nvidia, Tesla, OpenAI, and Amazon — broken down in plain English. Sorted by publication date, newest first.
Running a large language model on a GPU requires moving enormous amounts of weight data around — and that bandwidth cost is…
When you ask an AI a question, the quality of the answer depends almost entirely on what context gets fed into the…
Every time your GPU runs a task, the graphics driver spends time translating instructions into hardware commands. Intel's patent describes a way…
Getting an AI to write code is one thing — getting it to flag when it's probably wrong is another. Intel's new…
AMD is filing a patent for a GPU scheduling system that watches how your games actually run — across multiple frames —…
Instead of dumping raw survey responses on you, Salesforce wants a machine-learning model to digest that feedback and surface a synthesized summary…
Salesforce is patenting a way to keep two separate virtual workspaces — think channels or rooms — automatically in sync, so a…
Salesforce is teaching AI models to show their work — and only keep the answers where the reasoning actually checks out. The…
Apple is exploring a way to track a stylus using light rather than traditional capacitive touch — and the system can detect…
Lose cell signal on a hike and your iPhone currently just... gives up. Apple is patenting a system that instead tracks where…
Plain English, intelligent commentary, no hype.