LENS predicts NPU LLM inference latency with 2.15% mean error by profiling each bucket with two E2E measurements and composing results to capture bucketing non-linearity.
Forecasting llm inference performance via hardware-agnostic analytical modeling,
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3verdicts
UNVERDICTED 3representative citing papers
WattGPU ML models predict LLM inference power and latency on unseen GPUs with median errors of 3.4-13.5% using public data and show better performance than baselines.
Recover-LoRA with synthetic-data distillation recovers 80-95% accuracy on most benchmarks after selective 2-bit quantization of MLP gate/up layers while delivering 7.5-23.3% throughput improvement.
citing papers explorer
-
Recover-LoRA for Aggressive Quantization: Reclaiming Accuracy in 2-Bit Language Models via Low-Rank Adaptation with Knowledge Distillation on Synthetic Data
Recover-LoRA with synthetic-data distillation recovers 80-95% accuracy on most benchmarks after selective 2-bit quantization of MLP gate/up layers while delivering 7.5-23.3% throughput improvement.