FlashRT: Agent Harness for Guiding Agents to Deploy Real-Time Multimodal Applications

• URL: http://arxiv.org/abs/2607.18171v1
• Date: Mon, 20 Jul 2026 17:12:28 GMT
• Title: FlashRT: Agent Harness for Guiding Agents to Deploy Real-Time Multimodal Applications
• Abstract summary: Real-time multimodal applications compose heterogeneous models into pipelines.<n>Existing serving systems and auto-parallelism compilers commit to limited transformations and fixed workload assumptions.<n>We present FlashRT, an agent harness that guides coding agents to lift simple developer-written reference implementations into optimized multi- GPU deployments.
• Score: 28.58254460532054
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Real-time multimodal applications, including voice agents and interactive video generation, compose heterogeneous models into pipelines whose efficient deployment requires application-specific decisions about placement, streaming, and intra-model parallelism. Existing serving systems and auto-parallelism compilers commit to limited transformations and fixed workload assumptions, so achieving high performance on a new application requires hand-crafting an efficient implementation. We present FlashRT, an agent harness that guides coding agents to lift simple developer-written reference implementations into optimized multi-GPU deployments that flexibly weigh target metrics like latency and throughput. Using a new chain-of-program paradigm, FlashRT directs a generic coding agent through a multi-pass transformation process where an agent transforms the reference into an intermediate representation (IR) to capture data dependencies and persistent-state scopes, validates this IR via a sequential interpreter, and performs static analyses to identify candidate transformations. Then, the agent iteratively implements, verifies, and benchmarks each candidate under a measurement-gated optimization loop to produce effective deployments that span different hardware budgets. Across various applications, including video world models and multimodal LLMs, FlashRT converts reference implementations into highly efficient deployments, delivering up to ~70x latency reduction and 2.8x throughput improvement on NVIDIA B200 GPUs. On AMD MI355X GPUs, FlashRT matches the peak latency reduction while increasing peak throughput improvement to 3.6x, demonstrating that agent-driven optimization can be more scalable on platforms with less mature expert optimization. In fact, for Qwen3-Omni text-to-audio inference, FlashRT reduces response latency by 65% compared to the expert vLLM-Omni implementation on AMD MI355X.

Related papers

• Tiny Inference-Time Scaling with Latent Verifiers [56.696619768584675]
  Verifier on Hidden States ( VHS) operates on intermediate hidden representations of Diffusion Transformer (DiT) single-step generators.<n> VHS analyzes generator features without decoding to pixel space, thereby reducing the per-candidate verification cost.<n> VHS achieves a +2.7% improvement on GenEval at the same inference-time budget.
  arXiv  Detail & Related papers  (2026-03-23T19:00:02Z)
• Chimera: Latency- and Performance-Aware Multi-agent Serving for Heterogeneous LLMs [62.17306142810532]
  We present Chimera, a predictive scheduling system for multi-agent workflow serving on heterogeneous LLM clusters.<n>Chime traces the best latency, reducing end-to-end latency by 1.2--2.4$times$ and improving task performance by 8.0-9.5 percentage points on average over competitive baselines.
  arXiv  Detail & Related papers  (2026-03-23T17:01:42Z)
• Data Driven Optimization of GPU efficiency for Distributed LLM Adapter Serving [2.6336040306318274]
  Large Language Model (LLM) adapters enable low-cost model specialization.<n>LLM adapters introduce complex caching and scheduling challenges in distributed serving systems where hundreds of adapters must be hosted concurrently.<n>This paper presents a data-driven pipeline that computes an adapter placement that serves the workload with the minimum number of GPU.
  arXiv  Detail & Related papers  (2026-02-27T14:22:51Z)
• A Two-Stage GPU Kernel Tuner Combining Semantic Refactoring and Search-Based Optimization [9.49293344824955]
  This paper introduces a template-based rewriting layer on top of an agent-driven iterative loop.<n>The proposed method can be extended to deliver automated performance optimization for real production workloads.
  arXiv  Detail & Related papers  (2026-01-19T03:40:12Z)
• Eliminating Multi-GPU Performance Taxes: A Systems Approach to Efficient Distributed LLMs [61.953548065938385]
  We introduce the ''Three Taxes'' (Bulk Synchronous, Inter- Kernel Data Locality, and Kernel Launch Overhead) as an analytical framework.<n>We propose moving beyond the rigid BSP model to address key inefficiencies in distributed GPU execution.<n>We observe a 10-20% speedup in end-to-end latency over BSP-based approaches.
  arXiv  Detail & Related papers  (2025-11-04T01:15:44Z)
• Flash-Searcher: Fast and Effective Web Agents via DAG-Based Parallel Execution [48.7788770680643]
  Flash-Searcher is a novel parallel agent reasoning framework.<n>It decomposes complex tasks into subtasks with explicit dependencies, enabling concurrent execution of independent reasoning paths.<n>It achieves 67.7% accuracy on BrowseComp and 83% on xbench-DeepSearch, while reducing agent execution steps by up to 35% compared to current frameworks.
  arXiv  Detail & Related papers  (2025-09-29T17:39:30Z)
• Scalable Engine and the Performance of Different LLM Models in a SLURM based HPC architecture [3.746889836344766]
  This work elaborates on a High performance computing architecture based on Simple Linux Utility for Resource Management (SLURM)<n> Dynamic resource scheduling and seamless integration of containerized have been leveraged to manage CPU, GPU, and memory efficiently in multi-node clusters.<n>The obtained results pave ways for significantly more efficient, responsive, and fault-tolerant LLM inference on large-scale HPC infrastructures.
  arXiv  Detail & Related papers  (2025-08-25T09:11:27Z)
• Understanding and Optimizing Multi-Stage AI Inference Pipelines [11.254219071373319]
  HERMES is a Heterogeneous Multi-stage LLM inference Execution Simulator.<n> HERMES supports heterogeneous clients executing multiple models concurrently unlike prior frameworks.<n>We explore the impact of reasoning stages on end-to-end latency, optimal strategies for hybrid pipelines, and the architectural implications of remote KV cache retrieval.
  arXiv  Detail & Related papers  (2025-04-14T00:29:49Z)
• VectorLiteRAG: Latency-Aware and Fine-Grained Resource Partitioning for Efficient RAG [2.0929459605817193]
  Retrieval-Augmented Generation (RAG) systems combine vector similarity search with large language models (LLMs) to deliver context-aware responses.<n>We present VectorLiteRAG, a deployment-friendly RAG system that achieves latency-compliant inference without requiring additional hardware resources.
  arXiv  Detail & Related papers  (2025-04-11T19:18:41Z)
• Very Large-Scale Multi-Agent Simulation in AgentScope [112.98986800070581]
  We develop new features and components for AgentScope, a user-friendly multi-agent platform. We propose an actor-based distributed mechanism towards great scalability and high efficiency. We also provide a web-based interface for conveniently monitoring and managing a large number of agents.
  arXiv  Detail & Related papers  (2024-07-25T05:50:46Z)
• Energy-efficient Task Adaptation for NLP Edge Inference Leveraging Heterogeneous Memory Architectures [68.91874045918112]
  adapter-ALBERT is an efficient model optimization for maximal data reuse across different tasks. We demonstrate the advantage of mapping the model to a heterogeneous on-chip memory architecture by performing simulations on a validated NLP edge accelerator.
  arXiv  Detail & Related papers  (2023-03-25T14:40:59Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.