← 研踪 PaperTrailarXiv:2610.35309 · v3
Shared Context, Separate Engines: Stateful Streaming Inference for Multimodal LLMs on Edge SoCs
首次提交 2026-10-26 20:13
版本更新 2026-10-29 14:27
雷达观测 2026-10-30 11:25
摘要
Edge SoCs combine CPUs, GPUs, and NPUs, yet runtimes for multimodal large language models (MLLMs) keep generation on one engine and leave others idle. Streaming workloads allow ingestion and answering to overlap, but backend-local KV state binds queries to the engine that built their history. Stage performance and co-running interference vary, so no single placement wins across SoCs and workloads. \name separates logical history from engine-specific KV state so any language engine can continue a stream. Stateful Streaming Generation overlaps ingestion and answering, while Concurrent Sequence Generation serves ready queries in parallel. Phase-level state continuation lets one engine prefill a query and another decode the answer, freeing the first to resume ingestion. State-Driven Execution Planning (SDEP) chooses paths by predicted completion time and sets each engine's share of queries using arrival rates and measured service times. Across M4 Max, RK3588, and QCS6490, \name beats the strongest single-engine baselines, even when they reuse context. On M4 Max, SDEP cuts live-stream p95 time to first token by $76\%$, with every first token within one second, and raises throughput under backlog by up to $35\%$ over Metal-only execution with context reuse. On two RK3588 streams, SDEP delivers $19.6\%$ higher request throughput than the best single engine with context reuse and $27.2\%$ more than parallel engines without shared state. Stateful Streaming Generation reaches up to $2.48\times$ serial throughput on the same engines. Every answer matches its serial reference.
观测到的版本
相邻记录可能跳过中间版本；首次发现 v2 及以上也会标为版本更新。
v3 · 2026-10-29 14:27 · 最新观测版本
Shared Context, Separate Engines: Stateful Streaming Inference for Multimodal LLMs on Edge SoCs
Edge SoCs combine CPUs, GPUs, and NPUs, yet runtimes for multimodal large language models (MLLMs) keep generation on one engine and leave others idle. Streaming workloads allow ingestion and answering to overlap, but backend-local KV state binds queries to the engine that built their history. Stage performance and co-running interference vary, so no single placement wins across SoCs and workloads. \name separates logical history from engine-specific KV state so any language engine can continue a stream. Stateful Streaming Generation overlaps ingestion and answering, while Concurrent Sequence Generation serves ready queries in parallel. Phase-level state continuation lets one engine prefill a query and another decode the answer, freeing the first to resume ingestion. State-Driven Execution Planning (SDEP) chooses paths by predicted completion time and sets each engine's share of queries using arrival rates and measured service times. Across M4 Max, RK3588, and QCS6490, \name beats the strongest single-engine baselines, even when they reuse context. On M4 Max, SDEP cuts live-stream p95 time to first token by $76\%$, with every first token within one second, and raises throughput under backlog by up to $35\%$ over Metal-only execution with context reuse. On two RK3588 streams, SDEP delivers $19.6\%$ higher request throughput than the best single engine with context reuse and $27.2\%$ more than parallel engines without shared state. Stateful Streaming Generation reaches up to $2.48\times$ serial throughput on the same engines. Every answer matches its serial reference.
查看此版本解读 →查看此版本原文 ↗v2 · 2026-10-27 12:21
Shared Context, Separate Engines: Streaming Vision--Language Inference on Edge SoCs
Edge SoCs pack CPUs, GPUs, and NPUs, yet vision--language model (VLM) runtimes keep generation on one engine and leave the others idle. Streaming VLMs expose further parallelism: new frames arrive while earlier queries are still being answered. Engines differ in compute and memory access and contend when they co-run, so no single placement of stages wins across SoCs and workloads. Backend-local KV state keeps other engines from continuing the work. \name coordinates heterogeneous accelerators to execute stateful VLM inference concurrently. It separates a stream's versioned context from each engine's KV state, so any engine can continue the stream by reusing, importing, or reconstructing that state. Stateful Streaming Generation ingests new frames on one engine while another answers, and Concurrent Sequence Generation serves different ready requests in parallel. State-aware dispatch sends each request to the engine expected to finish it first. Each answer reads a fixed, published version of its history and matches its serial reference. \name beats the strongest single-engine baselines on Apple M4 Max, Rockchip RK3588, and Qualcomm QCS6490, even when they reuse context. On two RK3588 video streams, it delivers $19.6\%$ more throughput than the best single engine with context reuse and $27.2\%$ more than parallel engines without shared state. Cross-engine KV import cuts first-token latency by a factor of $4.6$ over prefix recomputation. Stateful Streaming Generation delivers up to $2.48\times$ the throughput of serial execution, and state-aware dispatch cuts query completion time by up to $72.7\%$.
查看此版本解读 →查看此版本原文 ↗