会员服务
AI Application Benchmarking: Power-Aware Performance Analysis for Vision and Language Models
Arxiv
0+阅读 · 6月19日
Accelerating Disaggregated RL for Visual Generative LLMs with Diffusion-Based Parallelism and Trainer-Assisted Generation
Arxiv
0+阅读 · 6月23日
Node-Level Performance and Energy Characterization of Flagship Science Applications on SuperMUC-NG Phase 2
Arxiv
0+阅读 · 6月22日
When Is a Columnar Scan Bandwidth-Bound? A Decode-Throughput Law and Its Cross-Hardware Validation
Arxiv
0+阅读 · 6月21日
CrossPool: Efficient Multi-LLM Serving for Cold MoE Models through KV-Cache and Weight Disaggregation
Arxiv
0+阅读 · 6月23日
FP8 is All You Need (Part 2): Efficient Ozaki-Bailey Style FFT Through Tensor-core Garner Reformulation and Kulisch Escape Route
Arxiv
0+阅读 · 5月28日
Randomized Sketching is Robust to Low-Precision Rounding on GPUs
Arxiv
0+阅读 · 6月18日
AI-PAVE-Br: Leveraging Large Language Models for Enhanced Product Attribute Value Extraction through a Golden Set Approach
Arxiv
0+阅读 · 6月23日
Look Before You Leap: Checking In on Type Tag Checking
Arxiv
0+阅读 · 6月18日
Memory Layouts for GPU-Data Transfer Buffering in SPH
Arxiv
0+阅读 · 6月22日
Does Mixture-of-Experts Actually Help Inference on Consumer and Edge Hardware? An Empirical Study
Arxiv
0+阅读 · 6月23日
LMS-AR: LMS Prediction-based Adaptive Regulator for Memory Bandwidth in Multicore Systems
Arxiv
0+阅读 · 6月22日
The Serialized Bridge: Understanding and Recovering LLM Serving Performance under Blackwell GPU Confidential Computing
Arxiv
0+阅读 · 6月22日
AI Tokenomics: The Economics of Tokens, Computation, and Pricing in Foundation Models
Arxiv
0+阅读 · 6月10日
Apple Neural Engine: Architecture, Programming, and Performance
Arxiv
0+阅读 · 6月21日
参考链接
微信扫码咨询专知VIP会员
Top