Quantizing models to lower precision formats, such as 8-bit or 4-bit, significantly reduces computational costs and accelerates inference. However, there has been a persistent question of whether these quantized models retain the same level of accuracy and quality. Recently, the machine learning (ML) community has raised significant concerns about whether quantized large language models (LLMs)… Read More We Ran Over Half a Million Evaluations on Quantized LLMs: Here's What We Found
Announcing LLM Compressor We are excited to announce LLM Compressor, a unified library for creating compressed models for faster inference with vLLM. Neural Magic's research team has successfully utilized it to create our latest compressed models, including fully quantized and accurate versions of Llama 3.1, and with that, we are excited to open up the… Read More LLM Compressor is Here: Faster Inference with vLLM
vLLM Now Supports FP8 on NVIDIA GPUs vLLM, a leading open-source LLM serving engine, has taken a significant leap forward in its recent 0.5 release by incorporating FP8 quantization support. This cutting-edge format promises to revolutionize LLM deployment by dramatically improving efficiency without sacrificing model quality. The implementation of FP8 support is the result of… Read More vLLM Brings FP8 Inference to the Open-Source Community
[Major Product News] Neural Magic Announces GPU Support for LLM Inference! Over the past several months, our team has been focused on expanding our capabilities to enable LLM inference on GPUs! A few weeks ago, we released our announcement of nm-vllm, our fork of vLLM, with a focus on incorporating the latest LLM optimizations like… Read More Neural Magic Product Release Update - Q1 2024
Announcing Community Support for GPU Inference Serving Over the past five years, Neural Magic has focused on accelerating inference of deep learning models on CPUs. To achieve this, we did two things: Many of the techniques we used to accelerate CPUs to make them more efficient can also help GPUs in their processing of LLMs.… Read More Bringing the Neural Magic to GPUs
For the last several months, we’ve been quite busy building out features across our libraries to enable large language model (LLM) inference on CPUs. We upgraded SparseML to support LLMs and generative models through transformers training, sparsification, and export pipelines. DeepSparse, Neural Magic’s inference runtime, has also been enhanced for performant LLM inference. Keep reading… Read More Neural Magic 1.6 Product Release
Key Takeaways This year has been an exceptionally exciting year for open-source large language models (LLMs). Just 11 months ago proprietary models, like GPT-3, were the only reasonable choice for companies to build generative AI applications. Now, there is a thriving ecosystem of high-quality open-source models, like Meta’s Llama family. In February, Meta released the… Read More Fast Llama 2 on CPUs With Sparse Fine-Tuning and DeepSparse
The AI space is abuzz with large language models (LLMs), but using them locally is a challenge due to their enormous size. Organizations that want to use these models for applications such as question answering must either invest in expensive cloud infrastructure or use closed-source models. By using closed-source models, companies also give up their… Read More Run a Medical Chatbot on CPUs With Sparse LLMs and DeepSparse
In the burgeoning field of AI, large language models (LLMs) currently dominate the headlines, producing applications that span from writing assistance to conversational AI. The popularity of these models is driven by their ability to generate text that is not only coherent but also contextually relevant. Default LLM inference pipelines operate by choosing the next… Read More Navigating the Nuances of Text Generation: How to Control LLM Outputs With DeepSparse
Since OpenAI's introduction of ChatGPT, developers worldwide have widely embraced the OpenAI API as the go-to solution for making API requests to their language models. However, in response to the growing demand within open-source communities for more accessible and cost-effective language model alternatives, users have started to explore the integration of DeepSparse with OpenAI's API.… Read More Integrating DeepSparse With OpenAI’s API for Fast Local LLMs