Skip to content
conftrace_

gpu memory management

7 papers

Explore in graph

Co-occurring keywords · papers mentioning both

large language model (3) long-context inference (2) inference serving (2) multi-level feedback queue (1) key-value cache offloading (1) zero-copy offloading (1) memory ballooning (1) tlb coherence (1) cpu pinned memory (1) latency-sensitive scheduling (1)

Papers

ECHO: Efficient KV Cache Offloading with Lossless Prefetching for Serving Native Sparse Attention LLMs OSDI 2026 FastServe: Iteration-Level Preemptive Scheduling for Large Language Model Inference NSDI 2026 MoonBright: A GPU Memory Allocator with Device-Side Page Table Materialization and Deferred TLB Coherence OSDI 2026 Nixie: Efficient, Transparent Temporal Multiplexing for Consumer GPUs OSDI 2026 No Buffer, No Bottleneck: Efficient Zero-Copy KV Cache Offloading for Long-Context LLMs OSDI 2026 Prism: Cost-Efficient Multi-LLM Serving via GPU Memory Ballooning OSDI 2026 DéjàVu: KV-cache Streaming for Fast, Fault-tolerant Generative LLM Serving ICML 2024