Showing 2026Show all
2 papers · 1 filter
cs.LG2026
The Joint Effect of Quantization and Sampling Temperature on LLM Safety Alignment: A Factorial Analysis
Hari Prasad, Ritam Pal
Modern LLM deployments often combine quantization with higher sampling temperatures to reduce cost, latency, or repetition, yet safety evaluations usually treat these as fixed impl…
cs.DC2026
LLM Inference at the Edge: Mobile, NPU, and GPU Performance Efficiency Trade-offs Under Sustained Load
Pranay Tummalapalli, Sahil Arayakandy, Ritam Pal +1
Deploying large language models on-device for always-on personal agents demands sustained inference from hardware tightly constrained in power, thermal envelope, and memory. We ben…