5 papers
Quantization-Aware Healing: A Practical Recipe for Recovering Compressed, 4-Bit LLMs
Bakbergen Ryskulov, Iker García-Ferrero, David Montero +5
Serving large language models cheaply increasingly means shipping models that are both structurally compressed to a fraction of their parameters and quantized to 4 bits. Together t…
Efficient Knowledge Distillation for LLMs: Offline Top-K Logits and a Fused Chunked KL Loss
Bakbergen Ryskulov, Iker García-Ferrero, Iker GarcÃa-Ferrero +7
Small language models are often the only option for deployment under tight latency, cost, and on-premises constraints, but they are rarely trained from scratch: a compressed model…
LLM Compression by Block Removal with Constrained Binary Optimization
David Jansen, Roman Rausch, Ali Hashemi +2
In this paper, we formulate the compression of large language models (LLMs) by optimally deleting transformer blocks (``block removal'') as a constrained binary optimization (CBO)…
Refusal Steering: Fine-grained Control over LLM Refusal Behaviour for Sensitive Topics
Iker GarcÃa-Ferrero, David Montero, Roman Orus
We introduce Refusal Steering, an inference-time method to exercise fine-grained control over Large Language Models refusal behaviour on politically sensitive topics without retrai…
Scaling Laws for Energy Efficiency of Local LLMs
Ander Alvarez, Alessandro Genuardi, Nilotpal Sinha +6
Deploying local large language models and vision-language models on edge devices requires balancing accuracy with constrained computational and energy budgets. Although graphics pr…