Sotabase

Career

· Research Intern, Apple2024–2024
· Intern, Microsoft2023–2023
· PhD Student, ETH Zurich2021–2025
· Research Assistant at Scalable Parallel Computing Lab, ETH Zurich2021–
· MS Student, Sharif University of Technology2016–2019
· Undergraduate Student, Isfahan University of Technology2010–2016

Publications (25)

GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers
arXiv.org · 2022
1,603
cited
QuaRot: Outlier-Free 4-Bit Inference in Rotated LLMs
Neural Information Processing Systems · 2024
355
cited
SpQR: A Sparse-Quantized Representation for Near-Lossless LLM Weight Compression
International Conference on Learning Representations · 2023
347
cited
OPTQ: Accurate Quantization for Generative Pre-trained Transformers
International Conference on Learning Representations · 2023
345
cited
SliceGPT: Compress Large Language Models by Deleting Rows and Columns
International Conference on Learning Representations · 2024
299
cited
Flare: Flexible In-Network Allreduce
International Conference for High Performance Computing, Networking, Storage and Analysis · 2021
54
cited
Motif Prediction with Graph Neural Networks
Knowledge Discovery and Data Mining · 2021
44
cited
QUIK: Towards End-to-end 4-Bit Inference on Generative Large Language Models
Conference on Empirical Methods in Natural Language Processing · 2023
35
cited
New Bounds For Distributed Mean Estimation and Variance Reduction
International Conference on Learning Representations · 2021
30
cited
ENS-10: A Dataset For Post-Processing Ensemble Weather Forecast
Neural Information Processing Systems · 2022
22
cited
Towards End-to-end 4-Bit Inference on Generative Large Language Models
arXiv.org · 2023
13
cited
Distributed Variance Reduction with Optimal Communication
2020
11
cited
ProbGraph: High-Performance and High-Accuracy Graph Mining with Probabilistic Set Representations
International Conference for High Performance Computing, Networking, Storage and Analysis · 2022
11
cited
Quartet: Native FP4 Training Can Be Optimal for Large Language Models
arXiv.org · 2025
9
cited
HALO: Hadamard-Assisted Lower-Precision Optimization for LLMs
arXiv.org · 2025
6
cited
STen: Productive and Efficient Sparsity in PyTorch
arXiv.org · 2023
6
cited
Bridging the Gap Between Promise and Performance for Microscaling FP4 Quantization
arXiv.org · 2025
5
cited
EfQAT: An Efficient Framework for Quantization-Aware Training
arXiv.org · 2024
5
cited
The spatial computer: A model for energy-efficient parallel computation
arXiv.org · 2022
5
cited
Computational Bottlenecks of Training Small-scale Large Language Models
ENLSP · 2024
4
cited
Sotabase
Saleh Ashkboos | Researcher Profile | Sotabase | Sotabase