会员服务
Multi-stage Flow Scheduling for LLM Serving
Arxiv
0+阅读 · 3月18日
Serving Hybrid LLM Loads with SLO Guarantees Using CPU-GPU Attention Piggybacking
Arxiv
0+阅读 · 3月17日
Efficient LLM Serving for Agentic Workflows: A Data Systems Perspective
Arxiv
0+阅读 · 3月17日
Nightjar: Dynamic Adaptive Speculative Decoding for Large Language Models Serving
Arxiv
0+阅读 · 3月3日
Nightjar: Dynamic Adaptive Speculative Decoding for Large Language Models Serving
Arxiv
0+阅读 · 2月22日
Semantic Parallelism: Redefining Efficient MoE Inference via Model-Data Co-Scheduling
Arxiv
0+阅读 · 2月27日
Real Money, Fake Models: Deceptive Model Claims in Shadow APIs
Arxiv
0+阅读 · 3月2日
Federated Inference: Toward Privacy-Preserving Collaborative and Incentivized Model Serving
Arxiv
0+阅读 · 3月4日
MoEless: Efficient MoE LLM Serving via Serverless Computing
Arxiv
0+阅读 · 3月6日
FLYING SERVING: On-the-Fly Parallelism Switching for Large Language Model Serving
Arxiv
0+阅读 · 3月2日
FLYING SERVING: On-the-Fly Parallelism Switching for Large Language Model Serving
Arxiv
0+阅读 · 2月26日
LLMServingSim 2.0: A Unified Simulator for Heterogeneous and Disaggregated LLM Serving Infrastructure
Arxiv
0+阅读 · 2月26日
MUSE: Multi-Tenant Model Serving With Seamless Model Updates
Arxiv
0+阅读 · 2月24日
BiScale: Energy-Efficient Disaggregated LLM Serving via Phase-Aware Placement and DVFS
Arxiv
0+阅读 · 2月21日
FlowPrefill: Decoupling Preemption from Prefill Scheduling Granularity to Mitigate Head-of-Line Blocking in LLM Serving
Arxiv
0+阅读 · 2月18日
参考链接
微信扫码咨询专知VIP会员
Top