9 papers
FastTPS: An Optimized Method for LLM Token Phase for AI accelerators
Wenzong Yang, Danyang Zhang, Kun Cao +17
The popularity of large language models (LLMs) escalates an ongoing demand for effective inference. However, due to the sequential processing of tokens during the token phase in de…
MINCE: Shrinking LLM Evaluation Datasets via Few-Model Monte Carlo Calibration
Devleena Das, Rajeev Patwari, Vikram Kumar Bukka +3
Evaluating LLMs across many model variants---quantized, fine-tuned, or deployment-specific---requires running large benchmarks repeatedly, a process that can take tens of hours per…
Ablation, Statistical Inference, and Validation for KV-Cache Compression
Paolo D'Alberto, Ashish Siarasao, Elliott Delaye +1
This study systematically compares Turbo-Quant and SpectralQuant KV-cache compression, evaluating non-dominated schemes, including WHT rotation with Beta Lloyd-Max and QJL, through…
Recover-LoRA for Aggressive Quantization: Reclaiming Accuracy in 2-Bit Language Models via Low-Rank Adaptation with Knowledge Distillation on Synthetic Data
Devleena Das, Rajeev Patwari, Elliott Delaye +1
Aggressive weight quantization to 2-bit precision offers substantial throughput and memory gains for large language model (LLM) inference, but typically incurs severe accuracy degr…
KV Pareto: Systems-Level Optimization of KV Cache and Model Compression for Long Context Inference
Sai Gokhale, Devleena Das, Rajeev Patwari +2
Long-context Large Language Models (LLMs) face significant memory bottlenecks during inference due to the linear growth of key-value (KV) cache with sequence length. While individu…
Recover-LoRA: Data-Free Accuracy Recovery of Degraded Language Models via Low-Rank Adaptation
Devleena Das, Rajeev Patwari, Ashish Sirasao
Inference optimizations such as quantization, pruning, format and datatype conversion, model export, and serialization can lead to functional degradations in language model task pe…
Forecasting LLM Inference Performance via Hardware-Agnostic Analytical Modeling
Rajeev Patwari, Ashish Sirasao, Devleena Das
Large language models (LLMs) have been increasingly deployed as local agents on personal devices with CPUs, NPUs and integrated GPUs. However, forecasting inference performance on…
Exploring the Dynamic Scheduling Space of Real-Time Generative AI Applications on Emerging Heterogeneous Systems
Rachid Karami, Rajeev Patwari, Hyoukjun Kwon +1
The integration of generative AI models, particularly large language models (LLMs), into real-time multi-model AI applications such as video conferencing and gaming is giving rise…
Analysis & Computational Complexity Reduction of Monocular and Stereo Depth Estimation Techniques
Rajeev Patwari, Varo Ly
Accurate depth estimation with lowest compute and energy cost is a crucial requirement for unmanned and battery operated autonomous systems. Robotic applications require real time…