Pruning LLMs Like a Physicist: Block Removal as an Ising Optimization Problem

Local-Minima-Preserving Continuous Relaxation of Ising Problems

arXiv:2606. 30333v1 Announce Type: cross Abstract: The generalized Ising problem captures a broad spectrum of hard combinatorial problems, including MAX-CUT, Number Partitioning (NPP), and Maximum Independent Set.

LLM Compression by Block Removal with Constrained Binary Optimization

arXiv:2602. 00161v2 Announce Type: replace-cross Abstract: 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) problem that can be mapped to a physical system (Ising glass), whose energies are a strong proxy for downstream model performance.

Preference Tuning LLMs with Direct Preference Optimization Methods

Optimizing your LLM in production

Fine-tuning LLMs to 1.58bit: extreme quantization made easy

A Fast and Effective Method for Euclidean Anticlustering: The Assignment-Based-Anticlustering Algorithm

arXiv:2601. 06351v2 Announce Type: replace Abstract: Anticlustering is an NP-hard combinatorial optimization problem that consists of partitioning a set of objects into equal-sized groups called anticlusters such that the objects in the same anticluster are as dissimilar as possible and thereby representative of the entire set of objects.

Making LLMs even more accessible with bitsandbytes, 4-bit quantization and QLoRA

How Benders Decomposition Works Part I: Optimality Cuts

A friendly introduction to one of the most powerfull optimization techniques using the uncapacitated facility location problem The post How Benders Decomposition Works Part I: Optimality Cuts appeared first on Towards Data Science .

Efficient Request Queueing – Optimizing LLM Performance

Bringing the Artificial Analysis LLM Performance Leaderboard to Hugging Face

Q-Strata: Hierarchical Bit Allocation for Mixed-Precision Quantization of Mixture-of-Experts LLMs

arXiv:2608.30564v1 Announce Type: cross Abstract: Mixed-precision quantization (MPQ) assigns a different bitwidth to each linear layer of a large language model (LLM) to minimize the quantization-ind...

Prefill and Decode for Concurrent Requests - Optimizing LLM Performance