Get your VLM running in 3 simple steps on Intel CPUs

Introducing AutoRound: Intel’s Advanced Quantization for LLMs and VLMs

Breaking the Ice: Analyzing Cold Start Latency in vLLM

arXiv:2606. 07362v1 Announce Type: new Abstract: As scalable inference services become popular, the cold start latency of an inference engine becomes important.

No GPU left behind: Unlocking Efficiency with Co-located vLLM in TRL

The Energy Blind Spot: NVIDIA's Flagship Edge AI Hardware Cannot Support Process-Level Energy Attribution

arXiv:2605. 27599v2 Announce Type: replace-cross Abstract: Agentic AI workloads - where a single user goal triggers multi-step orchestration, tool calls, retries, and failure recovery - are being targeted for edge deployment, with NVIDIA, Dell, HP, ASUS, MSI, Acer, and Gigabyte all shipping GB10-based desktop AI systems in 2026.

Accelerate your models with 🤗 Optimum Intel and OpenVINO

Accelerating Qwen3-8B Agent on Intel® Core™ Ultra with Depth-Pruned Draft Models

KernelGenBench: A Multi-Source and Multi-Chip Benchmark for LLM-based Kernel Generation

arXiv:2607. 27231v1 Announce Type: cross Abstract: Large language models (LLMs) have significantly increased the demand for efficient accelerator kernels, but kernel development remains a highly specialized and labor-intensive task.

nanoVLM: The simplest repository to train your VLM in pure PyTorch

ExaGEMM: Exploration Framework for CPU-Driven ML Inference via Associative In-Register Computing for Low-Bit GEMM

arXiv:2607. 14622v1 Announce Type: cross Abstract: Low-bit GEMM is increasingly central to efficient ML inference, yet very-low-bit execution remains a poor fit for conventional CPUs.

Low-Energy Reduced RISC-V Instruction Subset Processor for Tsetlin Machine Inference at the Edge

arXiv:2606. 19964v1 Announce Type: new Abstract: Tsetlin Machine (TM) is a logic-based machine learning approach that relies on simple bitwise operations and finite-state automata, which makes it attractive for edge AI deployments.

KernelSight-LM: A Kernel-Level LLM Inference Simulator

arXiv:2606. 28565v1 Announce Type: cross Abstract: As large language models (LLMs) move into production serving, practitioners must rapidly evaluate inference performance across diverse hardware, models, and serving parameters to meet cost and latency targets.

Optimizing CUDA like a Human: Micro-Profiling Tools as Expert Surrogates for LLM-Based GPU Kernel Optimization

arXiv:2606. 26453v1 Announce Type: new Abstract: We present KernelPro, a closed-loop multi-agent system that automatically generates, profiles, and iteratively optimizes GPU kernel code by integrating large language model (LLM) code generation with hardware profiler feedback and pluggable bottleneck detection tools.