A systems-level deep dive into the hidden microarchitectural costs of Kubernetes GPU time-slicing, and what it actually costs to co-locate Agentic AI workloads. The post GPU Time-Slicing for Concurrent LLM Agents on Kubernetes appeared first on Towards Data Science .
arXiv:2608. 12123v1 Announce Type: cross Abstract: LLM-agent services repeatedly execute small deterministic transitions between model and tool calls: route an outcome, update state, and emit the next effect.
arXiv:2608. 04458v1 Announce Type: new Abstract: Agentic AI is emerging in datacenters, but its architectural implications remain unexplored.
arXiv:2609.13585v1 Announce Type: cross Abstract: Communication has become a bottleneck in distributed training and inference of large models. Overlapping communication with computation at the granul...
Scepsy is a serving system designed to efficiently schedule arbitrary multi‑LLM agentic workflows on GPU clusters. It leverages the observation that each LLM’s share of execution time remains relatively stable across requests, profiling LLMs under various parallelism levels to build an Aggregate LLM Pipeline that predicts throughput and latency. Using this predictor, Scepsy searches for optimal GPU allocations—balancing fractional GPU shares, tensor parallelism, and replica counts—and then heuristically places them on the cluster to reduce fragmentation and honor network topology, achieving up to 2.5× higher throughput and 1.0–3.3× lower latency compared to baseline approaches.
KernelGenBench is a unified benchmark that evaluates large language models and agentic systems for generating efficient Triton kernels across diverse operator sources and hardware platforms. It covers 210 operators from PyTorch ATen, vLLM, and cuBLAS, and tests a 110‑operator subset on six different chips, consuming over 15 billion tokens in evaluation. The study finds that no single method dominates across all sources and platforms, with significant variations in correctness and performance depending on the operator source and hardware, and that agentic approaches require millions of tokens per successful operator.
arXiv:2608. 12629v1 Announce Type: new Abstract: GPU kernel agents and GPU programming languages have advanced separately, leaving expert kernels difficult to reproduce.
arXiv:2607. 19539v1 Announce Type: cross Abstract: Mixture-of-Experts (MoE) architectures increase model capacity without proportionally increasing computation cost and have become a key building block for scaling large language models (LLMs) to trillion-parameter regimes.
AgentPerfBench is a new benchmarking suite designed to evaluate the inference performance of agentic large language models (LLMs) that handle multi‑turn, tool‑using, and context‑expanding tasks. It builds on real traces from agentic benchmarks such as SWE‑Bench and TerminalBench, and generates synthetic profiles that reflect realistic input/output lengths and turn counts. The suite also provides kernel‑level Nsight Compute traces and a multi‑dimensional roofline model to identify hardware bottlenecks and quantify the gap between traditional chat benchmarks and agentic workloads.
arXiv:2512. 22219v2 Announce Type: replace-cross Abstract: We introduce Mirage Persistent Kernel (MPK), the first compiler and runtime system that automatically transforms multi-GPU model inference into a single high-performance mega-kernel.
arXiv:2604. 26963v2 Announce Type: replace-cross Abstract: Large language models (LLMs) are increasingly deployed as the execution core of autonomous agents rather than as standalone text generators.
arXiv:2607. 14541v1 Announce Type: new Abstract: Existing GPU kernel generation benchmarks draw problems from synthetic or curated sources that diverge from deployed workloads.
KernelOPT is a multi‑agent system that optimizes GPU kernels generated by compilers like PyTorch Inductor by treating compiled models as structured artifacts. It preserves vendor library calls and focuses on Triton sub‑kernels, using five profiling‑guided LLM agents and a four‑gate verification cascade to ensure correctness and performance before re‑stitching the model. On 250 KernelBench problems, KernelOPT achieves geometric mean speedups of 1.40×, 1.15×, and 1.07× over torch.compile at three optimization levels.