Execution-state capsules enable graph-bound full-state checkpointing and sub-millisecond restore for LLMs including KV and recurrent states, yielding 3.9x-27x TTFT speedups in on-device physical-AI serving.
Stateful Large Language Model Serving with Pensieve
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
abstract
Large Language Models (LLMs) are wildly popular today and it is important to serve them efficiently. Existing LLM serving systems are stateless across requests. Consequently, when LLMs are used in the common setting of multi-turn conversations, a growing log of the conversation history must be processed alongside any request by the serving system at each turn, resulting in repeated processing. In this paper, we design $Pensieve$, a system optimized for multi-turn conversation LLM serving. $Pensieve$ maintains the conversation state across requests by caching previously processed history to avoid duplicate processing. $Pensieve$'s multi-tier caching strategy can utilize both GPU and CPU memory to efficiently store and retrieve cached data. $Pensieve$ also generalizes the recent PagedAttention kernel to support attention between multiple input tokens with a GPU cache spread over non-contiguous memory. Our evaluation shows that $Pensieve$ can achieve $1.14$-$3.0\times$ the throughput of vLLM and TensorRT-LLM and significantly reduce latency.
years
2026 3representative citing papers
Balancing only first-turn agent requests while keeping follow-ups cache-aware raises LLM cluster TPS 10-16% (colocation) and prefill TPS 2-34% (disaggregation) over SOTA schedulers on production agent traces.
ITME uses CXL-hybrid memories for byte-addressable remote memory expansion in LLM inference, achieving up to 35.7% throughput improvement over conventional CPU-offloading.
citing papers explorer
-
Execution-State Capsules: Graph-Bound Execution-State Checkpoint and Restore for Low-Latency, Small-Batch, On-Device Physical-AI Serving
Execution-state capsules enable graph-bound full-state checkpointing and sub-millisecond restore for LLMs including KV and recurrent states, yielding 3.9x-27x TTFT speedups in on-device physical-AI serving.
-
SMetric: Rethink LLM Scheduling for Serving Agents with Balanced Session-centric Scheduling
Balancing only first-turn agent requests while keeping follow-ups cache-aware raises LLM cluster TPS 10-16% (colocation) and prefill TPS 2-34% (disaggregation) over SOTA schedulers on production agent traces.
-
ITME: Inference Tiered Memory Expansion with Disaggregated CXL-Hybrid Memories
ITME uses CXL-hybrid memories for byte-addressable remote memory expansion in LLM inference, achieving up to 35.7% throughput improvement over conventional CPU-offloading.