会员服务
ZipServ: Fast and Memory-Efficient LLM Inference with Hardware-Aware Lossless Compression
Arxiv
0+阅读 · 3月18日
ETM2: Empowering Traditional Memory Bandwidth Regulation using ETM
Arxiv
0+阅读 · 3月18日
This Is Taking Too Long -- Investigating Time as a Proxy for Energy Consumption of LLMs
Arxiv
0+阅读 · 3月16日
AI Application Benchmarking: Power-Aware Performance Analysis for Vision and Language Models
Arxiv
0+阅读 · 3月17日
Leveraging LLMs for Structured Information Extraction and Analysis from Cloud Incident Reports (Work In Progress Paper)
Arxiv
0+阅读 · 3月17日
Elastic Sketch under Random Stationary Streams: Limiting Behavior and Near-Optimal Configuration
Arxiv
0+阅读 · 3月17日
ETM2: Empowering Traditional Memory Bandwidth Regulation using ETM
Arxiv
0+阅读 · 3月17日
Tail Bounds for Queues with Abandonment: Constant, Moderate, Large Deviations, and Efficient Concentration
Arxiv
0+阅读 · 3月15日
SimLens for Early Exit in Large Language Models: Eliciting Accurate Latent Predictions with One More Token
Arxiv
0+阅读 · 3月14日
When Scanners Lie: Evaluator Instability in LLM Red-Teaming
Arxiv
0+阅读 · 3月15日
A Case for CATS: A Conductor-driven Asymmetric Transport Scheme for Semantic Prioritization
Arxiv
0+阅读 · 3月14日
MapReplay: Trace-Driven Benchmark Generation for Java HashMap
Arxiv
0+阅读 · 3月14日
A note on integrating products of linear forms over the unit simplex
Arxiv
0+阅读 · 3月13日
PreLoRA: Hybrid Pre-training of Vision Transformers with Full Training and Low-Rank Adapters
Arxiv
0+阅读 · 3月12日
TaxBreak: Unmasking the Hidden Costs of LLM Inference Through Overhead Decomposition
Arxiv
0+阅读 · 3月12日
参考链接
微信扫码咨询专知VIP会员
Top