aiqbench analysis
This research demonstrates significant efficiency gains by implementing 2-bit microkernels on modern CPUs and Intel Xe2 GPUs, achieving up to a 7× speedup over standard 16-bit inference pipelines. By optimizing runtimes for ultra-low-bit quantized models, the study addresses critical bottlenecks in latency, memory usage, and energy consumption without sacrificing model accuracy. This work is essential for deploying large language models at scale where hardware constraints are paramount.
Pushing the Envelope of LLM Inference with Ultra-Low-Bit Quantized Models
arXiv:2508.06753v3 Announce Type: replace Abstract: The advent of ultra-low-bit LLM models, approaching the perplexity and task accuracy of their full precision counterparts, is ushering in a new era of LLM inference. While these advances promise models that are cost-effective regarding latency, memory, throughput, and energy consumption, the efficiency of runtimes for deploying ultra-low-bit models remains under-explored. In this work, we take a bottom-up approach: we first implement 2-bit microkernels for modern CPUs, achieving close-to-roofline performance. We integrate these microkernels into LLM inference pipelines and present end-to-end results with 2-bit models, outperforming the state-of-the-art (SOTA) bitnet.cpp runtime by 2.2$\times$, and deliver up to 7$\times$ speedup compared to 16-bit inference. We extend this work to Intel Xe2 GPUs where we implement mixed-precision, 2-bit kernels, and show their performance to be close-to-optimal. We integrated the GPU kernels in the vLLM framework and evaluated end-to-end inference for a range of models and Xe2 GPUs. We obtain up to 6.7$\times$ speedup compared to the 16-bit pipeline, pushing the envelope of LLM inference.
Abstract:The advent of ultra-low-bit LLM models, approaching the perplexity and task accuracy of their full precision counterparts, is ushering in a new era of LLM inference. While these advances promise models that are cost-effective regarding latency, memory, throughput, and energy consumption, the efficiency of runtimes for deploying ultra-low-bit models remains under-explored. In this work, we take a bottom-up approach: we first implement 2-bit microkernels for modern CPUs, achieving close-to-roofline performance. We integrate these microkernels into LLM inference pipelines and present end-to-end results with 2-bit models, outperforming the state-of-the-art (SOTA) this http URL runtime by 2.2$\times$, and deliver up to 7$\times$ speedup compared to 16-bit inference. We extend this work to Intel Xe2 GPUs where we implement mixed-precision, 2-bit kernels, and show their performance to be close-to-optimal. We integrated the GPU kernels in the vLLM framework and evaluated end-to-end inference for a range of models and Xe2 GPUs. We obtain up to 6.7$\times$ speedup compared to the 16-bit pipeline, pushing the envelope of LLM inference.
Artificial Intelligence (cs.AI); Machine Learning (cs.LG); Performance (cs.PF)
arXiv:2508.06753 [cs.AI]
(or arXiv:2508.06753v3 [cs.AI] for this version)
https://doi.org/10.48550/arXiv.2508.06753 Focus to learn more arXiv-issued DOI via DataCite
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 261 words
Related coverage
[AINews] High Taste Testers Ep. 1
Latent Space · Oct 17, 2026
[AINews] DeepSeek v4.1-Flash: 763B-P8B-D16B novel causal Encoder–Decoder architecture with vision marks the Return of the Whale
Latent Space · Sep 12, 2026
[AINews] Meta Muse Wonder & Wonder Full: MSL’s Claude 5.5-tier Frontier Model
Latent Space · Oct 13, 2026
[AINews] not much happened today
Latent Space · Oct 3, 2026