works on

From the 1 of 9 linked papers with an AI index.

collaborators

9 papers

cs.LG2026

FastTPS: An Optimized Method for LLM Token Phase for AI accelerators

Wenzong Yang, Danyang Zhang, Kun Cao +17

FastTPS is a set of techniques that reduce memory traffic and fuse operations during the token‑phase of large language model inference on AI accelerators, achieving up to a 6× spee…

cs.AI2026

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 p…

cs.LG2026

UltraQuant: 4-bit KV Caching for Context-Heavy Agents

Inesh Chakrabarti, David Limpus, Aditi Ghai Rana +4

Context-heavy agents place unusual pressure on the key-value (KV) cache: long prefixes are reused across many short turns, while concurrency determines whether the serving system c…

cs.LG2026

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…

cs.CR2026

Privatar: Scalable Privacy-preserving Multi-user VR via Secure Offloading

Jianming Tong, Hanshen Xiao, Krishna Kumar Nair +5

Multi-user virtual reality enables immersive interaction. However, rendering avatars for numerous participants on each headset incurs prohibitive computational overhead, limiting s…

cs.LG2025

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…