会员服务
ZipServ: Fast and Memory-Efficient LLM Inference with Hardware-Aware Lossless Compression
Arxiv
0+阅读 · 3月18日
HierarchicalKV: A GPU Hash Table with Cache Semantics for Continuous Online Embedding Storage
Arxiv
0+阅读 · 3月17日
LUMINA: LLM-Guided GPU Architecture Exploration via Bottleneck Analysis
LUMINA: LLM-Guided GPU Architecture Exploration via Bottleneck Analysis
Arxiv
0+阅读 · 3月18日
The 1/W Law: An Analytical Study of Context-Length Routing Topology and GPU Generation Gains for LLM Inference Energy Efficiency
Arxiv
0+阅读 · 3月18日
AI Application Benchmarking: Power-Aware Performance Analysis for Vision and Language Models
Arxiv
0+阅读 · 3月17日
Fluids You Can Trust: Property-Preserving Operator Learning for Incompressible Flows
Fluids You Can Trust: Property-Preserving Operator Learning for Incompressible Flows
Arxiv
0+阅读 · 3月17日
Towards heterogeneous parallelism for SPHinXsys
Arxiv
0+阅读 · 3月17日
ODIN-Based CPU-GPU Architecture with Replay-Driven Simulation and Emulation
Arxiv
0+阅读 · 3月17日
Dataflow-Oriented Classification and Performance Analysis of GPU-Accelerated Homomorphic Encryption
Arxiv
0+阅读 · 3月17日
FleetOpt: Analytical Fleet Provisioning for LLM Inference with Compress-and-Route as Implementation Mechanism
Arxiv
0+阅读 · 3月17日
inference-fleet-sim: A Queueing-Theory-Grounded Fleet Capacity Planner for LLM Inference
Arxiv
0+阅读 · 3月17日
Serving Hybrid LLM Loads with SLO Guarantees Using CPU-GPU Attention Piggybacking
Arxiv
0+阅读 · 3月17日
Guaranteeing Semantic and Performance Determinism in Flexible GPU Sharing
Arxiv
0+阅读 · 3月17日
An Efficient Heterogeneous Co-Design for Fine-Tuning on a Single GPU
Arxiv
0+阅读 · 3月17日
Guaranteeing Semantic and Performance Determinism in Flexible GPU Sharing
Arxiv
0+阅读 · 3月16日
参考链接
微信扫码咨询专知VIP会员
Top