This work integrates SmoothQuant into TorchAO and optimize the resulting inference path for Intel Xeon CPUs through graph-level fusion in TorchInductor and efficient INT8 GEMM kernel selection across oneDNN-, AVX512_VNNI-, and AMX-based implementations.
Abstract
Small NLP models, especially BERT-family encoders, remain important in industrial workloads such as classification, ranking, and retrieval even in the era of large language models. On server CPUs, INT8 quantization offers an attractive latency-throughput-cost trade-off, but users increasingly expect such acceleration to be available directly in the native PyTorch stack. We integrate SmoothQuant into TorchAO and optimize the resulting inference path for Intel Xeon CPUs through graph-level fusion in TorchInductor and efficient INT8 GEMM kernel selection across oneDNN-, AVX512_VNNI-, and AMX-based implementations. Across BERT, DistilBERT, and XLM-RoBERTa benchmarks, the approach delivers up to 5.8x end-to-end throughput speedup with negligible---and in some cases no measurable---accuracy loss relative to the FP32 baseline. We also validated our work by detailed performance analysis with roofline models. The implementation has been upstreamed to PyTorch and TorchAO, enabling out-of-the-box deployment with native PyTorch tooling
Deploying large language models in realistic server environments poses challenges, as the system needs to provide high-quality responses with low latency. Quantization is a common approach to reduce the memory footprint and improve inference efficiency, yet its impact on latency and throughput is rarely evaluated under controlled, orchestration-level workloads. In this work we study the quantization trade-offs of two translation model families, EuroLLM \citep{martins2025eurollm} and Hy-MT2 \citep{zheng2026hy} across five models ranging from 1.7B to 22B for efficient deployment on a single A100 or H100 GPU. We demonstrate that combining a document-chunking strategy with W4A8 or W8A8 quantization improves the latency-throughput Pareto-curve under a wide range of workloads. Furthermore, since standard machine translation (MT) benchmarks rely on isolated sentences and fail to capture long-context dynamics, we introduce a document-level evaluation from WMT24++ to assess how text chunking strategies affect translation quality under quantization. Our results reveal that standard segment-level evaluation can fail to predict the interaction between quantization and long-context document translation. While Hy-MT2 remains robust under quantization, EuroLLM shows strong sensitivity and translation quality collapses rapidly for all considered quantization formats. Overall, our experiments show that the trade-off between inference efficiency and translation quality depends not only on the quantization format, but also on the choice of text chunking strategy.
Jim Zhao, Sohir Maskey, Koen Oostermeijer et al.· 0 citations
Large Language Models (LLMs) achieve state-of-the-art performance across natural language processingtasks but remain computationally intensive, limiting their deployment in browser-based environments.This study investigates the feasibility of real-time transformer inference entirely within web browsers usingWebGPU acceleration. We propose a lightweight BERT-inspired architecture optimized for GPUparallelmatrix operations through TensorFlow.js with the WebGPU backend. The model is evaluated ona 4,000-sample IMDB sentiment classification dataset and achieves 65–70% classification accuracy withper-sample inference latency of 8–9 ms in Google Chrome using an NVIDIA T400 GPU (4 GB VRAM).Batch inference throughput reaches approximately 6,600 inferences per minute, while GPU utilization remainsstable between 26–77%. Compared to CPU-based TensorFlow.js execution, WebGPU significantlyreduces inference latency and enables fully client-side training and inference without server dependencies.Although accuracy is lower than full-scale BERT benchmarks, the results demonstrate that simplified transformerarchitectures can operate efficiently in browser environments under resource constraints. This workestablishes a practical framework for deploying real-time edge NLP applications using open web standardsand GPU acceleration.
Md Istiak Morsalin, Tasnim Akter Onisha, A. Shalan et al.· Informatica· 0 citations
This work presents a systematic, empirical comparison of contemporary compression techniques for large language models (LLMs), namely quantization, pruning, and parameter-efficient fine-tuning (PEFT) using a representative set of open-source model families (Llama, Mistral, Phi and Qwen) and model scales (1.7 Billion to 70 Billion). Evaluation combined benchmarks (MMLU, SQuAD v2, TinyBenchmarks and WikiText), deployment metrics (peak memory, time-to-first-token, tokens/sec and maximum sequence lengths) and settings (multi-GPU clusters, single-GPU PC, laptop, and smartphone) to capture real-world trade-offs. Quantization often delivered the best wins for deployment feasibility—enabling single-device and mobile inference—but required careful per-model tuning and backend support to avoid throughput regressions. Pruning reduced parameter counts substantially but frequently incured large, even catastrophic, performance loss beyond moderate sparsity levels. Retraining partially mitigated this but did not uniformly close the gap to quantization. Finally, PEFT methods enabled models to match or outperform models with up to 18 times the parameters on SQuAD v2 while reducing storage as well as optimizer overhead and often improved task performance even when full fine-tuning failed.
Dominik Hildebrand, Benjamin Kiefer, Andreas Zell· Artificial Intelligence Revi...· 0 citations
GPUs increasingly accelerate database systems, but query-specific peak performance still often relies on hand-written kernels. Existing LLM kernel benchmarks focus on machine learning operators, leaving irregular, heterogeneous, data-movement-heavy database-style operators untested. We introduce DataKernelBench, which translates SQL into validated PyTorch TorchPlan programs and evaluates LLMs that optimize either the core tensor-bounded snippet or the full query in CUDA or Triton through execution-guided repair. Across ten proprietary and open-weight models on TPC-H SF10 with an H100 GPU, the strongest full-query CUDA configuration achieves $2.11\times$ speedup over the TorchPlan baseline at full pass rate. We find that higher-performing implementations commonly use kernel fusion and execution-strategy changes, stronger models benefit most from full-query specialization, and workload context matters more than hardware context. To handle data larger than GPU memory, we extend TorchPlan with Dask-cuDF for on-demand partition loading on TPC-H SF100 with four H100 GPUs, achieving $2.54\times$ speedup. Project page: https://kerneldf.github.io/datakernelbench
As LLM inference shifts to multi-tenant GPU clusters, co-batching improves throughput but obscures per-tenant usage and limits control. Enabling fractional sharing of the inference engine requires a real-time, per-request attribution primitive that is accurate and light enough to run inside the scheduling loop. We present LLMVisor, a roofline-guided latency attribution model that captures the memory-bound and compute-bound phases via a concise piecewise-linear form over features proportional to FLOPs and memory I/O traffic. LLMVisor decomposes batch latency into additive, per-request shares and runs efficiently at microsecond scale. We evaluate LLMVisor across Llama 3.1-8B and Qwen 2.5-14B/32B on A100/H100 GPUs under varying tensor parallelism and workload mixes. Compared to a token-count baseline, LLMVisor attains near-perfect R-squared and reduces relative error by up to 2.5x and 3.3x at p90 and p99, respectively, for prefill, and by up to 3.5x and 4.4x for decode, despite batching variability and sequence divergence.
Shuowei Jin, Xueshen Liu, Jiaxin Shan et al.· 2 citations
The design of transformer-based Large Language Models (LLMs) is being radically changed through new architectures that are able to overcome scalability limitations of previous designs, including Mixture-of-Experts (MoE), Multi-Head Latent Attention (MLA), and Multi-Token Prediction (MTP). As an open-weighted model released at the end of 2024, which has both state of the art architectural transparency and production scale efficiency, DeepSeeek-V3 represents the ultimate testing ground for investigating these modern technologies. This paper provides a comprehensive analysis of the architectural structure of DeepSeek-V3 based upon information from the DeepSeek-V3 Technical Report, industry benchmarking data and independent latency testing, to demonstrate how various techniques can be used to optimize training while still providing competitive performance in code generation and mathematical reasoning. In addition, latency testing conducted on a Distilled version of DeepSeek-V3, with approximately 14 billion parameters, running on a T4 GPU, reveals that although significant improvements have been made in optimizing latency there remains substantial barriers to deploying these models. Through this context, this research will serve as a reference document for practitioners and researchers who wish to understand current trends and challenges in increasing accessibility to high performance AI models.
Yassine Zouhdi, B. Hdioud· EPJ Web of Conferences· 0 citations
What if pathology foundation models could do more with less? GigaPath-Flash and GigaTIME-Flash cut computational demands while maintaining strong performance, opening the door to larger studies and broader exploration. The post GigaPath-Flash and GigaTIME-Flash: Toward population-scale discovery with efficient pathology foundation models appeared first on Microsoft Research.
MIT News · Artificial Intelligence· news.mit.eduAug 31, 2026
With millions of users across the world, Julia has been used to conduct cutting-edge research and to design new drugs, jet engines, heat pumps, and more.