会员服务
ML-Based Optimum Sub-system Size Heuristic for the GPU Implementation of the Tridiagonal Partition Method
Arxiv
0+阅读 · 10月31日
Accelerating Mixture-of-Experts Inference by Hiding Offloading Latency with Speculative Decoding
Arxiv
0+阅读 · 10月31日
AMD MI300X GPU Performance Analysis
AMD MI300X GPU Performance Analysis
Arxiv
0+阅读 · 10月31日
Intelligent Software System for Low-Cost, Brightfield Segmentation: Algorithmic Implementation for Cytometric Auto-Analysis
Intelligent Software System for Low-Cost, Brightfield Segmentation: Algorithmic Implementation for Cytometric Auto-Analysis
Arxiv
0+阅读 · 10月31日
Tokencake: A KV-Cache-centric Serving Framework for LLM-based Multi-Agent Applications
Arxiv
0+阅读 · 10月31日
Dynamic Risk Assessments for Offensive Cybersecurity Agents
Arxiv
0+阅读 · 10月30日
Running VLAs at Real-time Speed
Running VLAs at Real-time Speed
Arxiv
0+阅读 · 10月30日
Inference-Cost-Aware Dynamic Tree Construction for Efficient Inference in Large Language Models
Arxiv
0+阅读 · 10月30日
Analysis and Optimized CXL-Attached Memory Allocation for Long-Context LLM Fine-Tuning
Arxiv
0+阅读 · 10月30日
VeriLLM: A Lightweight Framework for Publicly Verifiable Decentralized Inference
Arxiv
0+阅读 · 10月30日
GPU-Accelerated Primal Heuristics for Mixed Integer Programming
Arxiv
0+阅读 · 10月30日
Oneiros: KV Cache Optimization through Parameter Remapping for Multi-tenant LLM Serving
Arxiv
0+阅读 · 10月29日
mitransient: Transient light transport in Mitsuba 3
Arxiv
0+阅读 · 10月29日
Dynamic Risk Assessments for Offensive Cybersecurity Agents
Arxiv
0+阅读 · 10月29日
Scalable GPU-Based Integrity Verification for Large Machine Learning Models
Arxiv
0+阅读 · 10月27日
参考链接
微信扫码咨询专知VIP会员
Top