Apple and NVIDIA shared details of a collaboration to improve the performance of LLMs with a new text generation technique for AI. Cupertino writes:
Accelerating LLM inference is an important ML research problem, as auto-regressive token generation is computationally expensive and relatively slow, and improving inference efficiency can reduce latency for users. In addition to ongoing efforts to accelerate inference on Apple silicon, we have recently made significant progress in accelerating LLM inference for the NVIDIA GPUs widely used for production applications across the industry.
Earlier this year, Apple published and open-sourced Recurrent Drafter (ReDrafter), which is a novel approach to speculative decoding that “achieves state of the art performance.” According to the company, ReDrafter uses an RNN draft model, and combines beam search with dynamic tree attention to speed up LLM token generation by up to 3.5 tokens per generation step for open source models, surpassing the performance of prior speculative decoding techniques.
“In benchmarking a tens-of-billions parameter production model on NVIDIA GPUs, using the NVIDIA TensorRT-LLM inference acceleration framework with ReDrafter, we have seen 2.7x speed-up in generated tokens per second for greedy decoding,” Apple papers show. With that, this technology could signifanctly reduce latency users may experience, while also using fewer GPUs and consuming less power.
This is especially useful as Apple keeps improving its Apple Intelligence platform. By offering faster and more accurated results, users will have a better experience when using Apple’s AI tools. The company finishes its paper by saying ReDrafter can improve the experience with NVIDIA’s GPUs:
Tech. Entertainment. Science. Your inbox.
Sign up for the most interesting tech & entertainment news out there.
Email: SIGN UP
By signing up, I agree to the Terms of Use and have reviewed the Privacy Notice.
LLMs are increasingly being used to power production applications, and improving inference efficiency can both impact computational costs and reduce latency for users. With ReDrafter’s novel approach to speculative decoding integrated into the NVIDIA TensorRT-LLM framework, developers can now benefit from faster token generation on NVIDIA GPUs for their production LLM applications.
If you’re a developer and want to use the new ReDrafter tool, you can find detailed information on both Apple’s website and NVIDIA’s developer blog.
The post NVIDIA is helping Apple build a faster and better AI experience appeared first on BGR.
