51 citations · 87 across the 14 of their papers we have counts for
15 papers
MonoMoE: An Efficient Fused Mega-kernel for Quantized MoE Decoding
Yu Gong, Kailash Budhathoki, Taeho Kim +2
Mixture-of-Experts (MoE) layers increase model capacity without proportionally increasing arithmetic, but their sparse expert computation is difficult to execute efficiently during…
When LLMs get significantly worse: A statistical approach to detect model degradations
Jonas Kübler, Kailash Budhathoki, Matthäus Kleindessner +4
Minimizing the inference cost and latency of foundation models has become a crucial area of research. Optimization approaches include theoretically lossless methods and others with…
Block-Diagonal LoRA for Eliminating Communication Overhead in Tensor Parallel LoRA Serving
Xinyu Wang, Jonas M. Kübler, Kailash Budhathoki +2
When serving a single base LLM with several different LoRA adapters simultaneously, the adapters cannot simply be merged with the base model's weights as the adapter swapping would…
A Proximal Operator for Inducing 2:4-Sparsity
Jonas M Kübler, Yu-Xiang Wang, Shoham Sabach +5
Recent hardware advancements in AI Accelerators and GPUs allow to efficiently compute sparse matrix multiplications, especially when 2 out of 4 consecutive weights are set to zero.…
LLM-Rank: A Graph Theoretical Approach to Pruning Large Language Models
David Hoffmann, Kailash Budhathoki, Matthaeus Kleindessner
The evolving capabilities of large language models are accompanied by growing sizes and deployment costs, necessitating effective inference optimisation techniques. We propose a no…
Inference Optimization of Foundation Models on AI Accelerators
Youngsuk Park, Kailash Budhathoki, Liangfu Chen +7
Powerful foundation models, including large language models (LLMs), with Transformer architectures have ushered in a new era of Generative AI across various industries. Industry an…
Evaluating the Fairness of Discriminative Foundation Models in Computer Vision
Junaid Ali, Matthaeus Kleindessner, Florian Wenzel +3
We propose a novel taxonomy for bias evaluation of discriminative foundation models, such as Contrastive Language-Pretraining (CLIP), that are used for labeling tasks. We then syst…
Meaningful Causal Aggregation and Paradoxical Confounding
Yuchen Zhu, Kailash Budhathoki, Jonas Kuebler +1
In aggregated variables the impact of interventions is typically ill-defined because different micro-realizations of the same macro-intervention can result in different changes of…
Explaining the root causes of unit-level changes
Kailash Budhathoki, George Michailidis, Dominik Janzing
Existing methods of explainable AI and interpretable ML cannot explain change in the values of an output variable for a statistical unit in terms of the change in the input values…
DoWhy-GCM: An extension of DoWhy for causal inference in graphical causal models
Patrick Blöbaum, Peter Götz, Kailash Budhathoki +2
We present DoWhy-GCM, an extension of the DoWhy Python library, which leverages graphical causal models. Unlike existing causality libraries, which mainly focus on effect estimatio…
Why did the distribution change?
Kailash Budhathoki, Dominik Janzing, Patrick Bloebaum +1
We describe a formal approach based on graphical causal models to identify the "root causes" of the change in the probability distribution of variables. After factorizing the joint…
Discovering Reliable Causal Rules
Kailash Budhathoki, Mario Boley, Jilles Vreeken
We study the problem of deriving policies, or rules, that when enacted on a complex system, cause a desired outcome. Absent the ability to perform controlled experiments, such rule…
Quantifying intrinsic causal contributions via structure preserving interventions
Dominik Janzing, Patrick Blöbaum, Atalanti A. Mastakouri +3
We propose a notion of causal influence that describes the `intrinsic' part of the contribution of a node on a target node in a DAG. By recursively writing each node as a function…
Causal structure based root cause analysis of outliers
Dominik Janzing, Kailash Budhathoki, Lenon Minorics +1
We describe a formal approach to identify 'root causes' of outliers observed in variables in a scenario where the causal relation between the variables is a kno…
Causal Inference by Stochastic Complexity
Kailash Budhathoki, Jilles Vreeken
The algorithmic Markov condition states that the most likely causal direction between two random variables X and Y can be identified as that direction with the lowest Kolmogorov co…