会员服务
ZipServ: Fast and Memory-Efficient LLM Inference with Hardware-Aware Lossless Compression
Arxiv
0+阅读 · 3月18日
Photonic Rails in ML Datacenters with Opus
Arxiv
0+阅读 · 3月17日
Towards heterogeneous parallelism for SPHinXsys
Arxiv
0+阅读 · 3月17日
Unifying Optimization and Dynamics to Parallelize Sequential Computation: A Guide to Parallel Newton Methods for Breaking Sequential Bottlenecks
Arxiv
0+阅读 · 3月17日
Parallelised Differentiable Straightest Geodesics for 3D Meshes
Arxiv
0+阅读 · 3月16日
Early-Terminable Energy-Safe Iterative Coupling for Parallel Simulation of Port-Hamiltonian Systems
Arxiv
0+阅读 · 3月17日
Intrinsic Sequentiality in P: Causal Limits of Parallel Computation
Arxiv
0+阅读 · 3月17日
Nova: Scalable Streaming Join Placement and Parallelization in Resource-Constrained Geo-Distributed Environments
Nova: Scalable Streaming Join Placement and Parallelization in Resource-Constrained Geo-Distributed Environments
Arxiv
0+阅读 · 3月16日
Fold-CP: A Context Parallelism Framework for Biomolecular Modeling
Arxiv
0+阅读 · 3月16日
TurboMap: GPU-Accelerated Local Mapping for Visual SLAM
Arxiv
0+阅读 · 3月16日
Committee Configuration Optimization for Parallel Byzantine Consensus in a Trusted Execution Environment
Arxiv
0+阅读 · 3月15日
NCCL EP: Towards a Unified Expert Parallel Communication API for NCCL
Arxiv
0+阅读 · 3月13日
Exploiting temporal parallelism for LSTM Autoencoder acceleration on FPGA
Arxiv
0+阅读 · 3月14日
Justitia: Fair and Efficient Scheduling of Task-parallel LLM Agents with Selective Pampering
Arxiv
0+阅读 · 3月14日
ComFree-Sim: A GPU-Parallelized Analytical Contact Physics Engine for Scalable Contact-Rich Robotics Simulation and Control
Arxiv
0+阅读 · 3月14日
参考链接
微信扫码咨询专知VIP会员
Top