Roberto L. Castro

According to our database, Roberto L. Castro authored at least 11 papers between 2020 and 2025.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of four.

2025

Quartet: Native FP4 Training Can Be Optimal for Large Language Models.

Roberto L. Castro, Andrei Panferov, Soroush Tabesh, Oliver Sieberling, Jiale Chen, Mahdi Nikdan, Saleh Ashkboos, Dan Alistarh

CoRR, May, 2025

QuEST: Stable Training of LLMs with 1-Bit Weights and Activations.

Andrei Panferov, Jiale Chen, Soroush Tabesh, Roberto L. Castro, Mahdi Nikdan, Dan Alistarh

CoRR, February, 2025

HALO: Hadamard-Assisted Lower-Precision Optimization for LLMs.

Saleh Ashkboos, Mahdi Nikdan, Soroush Tabesh, Roberto L. Castro, Torsten Hoefler, Dan Alistarh

CoRR, January, 2025

MARLIN: Mixed-Precision Auto-Regressive Parallel Inference on Large Language Models.

Elias Frantar, Roberto L. Castro, Jiale Chen, Torsten Hoefler, Dan Alistarh

Proceedings of the 30th ACM SIGPLAN Annual Symposium on Principles and Practice of Parallel Programming, 2025

Adapt-S: Effective DNN Pruning via Unified Accuracy and Performance Tuning.

Roberto L. Castro, Diego Andrade, Basilio B. Fraguela

Proceedings of the IEEE International Parallel and Distributed Processing Symposium, 2025

2024

MARLIN: Mixed-Precision Auto-Regressive Parallel Inference on Large Language Models.

Elias Frantar, Roberto L. Castro, Jiale Chen, Torsten Hoefler, Dan Alistarh

Dataset, November, 2024

STuning-DL: Model-Driven Autotuning of Sparse GPU Kernels for Deep Learning.

Roberto L. Castro, Diego Andrade, Basilio B. Fraguela

IEEE Access, 2024

2023

VENOM: A Vectorized N: M Format for Unleashing the Power of Sparse Tensor Cores.

Roberto L. Castro, Andrei Ivanov, Diego Andrade, Tal Ben-Nun, Basilio B. Fraguela, Torsten Hoefler

Proceedings of the International Conference for High Performance Computing, 2023

2022

Probing the Efficacy of Hardware-Aware Weight Pruning to Optimize the SpMM Routine on Ampere GPUs.

Roberto L. Castro, Diego Andrade, Basilio B. Fraguela

Proceedings of the International Conference on Parallel Architectures and Compilation Techniques, 2022

2020

Reusing Trained Layers of Convolutional Neural Networks to Shorten Hyperparameters Tuning Time.

Roberto L. Castro, Diego Andrade, Basilio B. Fraguela

CoRR, 2020

A Hybrid Approach for Tracking Individual Players in Broadcast Match Videos.

Roberto L. Castro, Diego Andrade, Basilio B. Fraguela

CoRR, 2020