Andrew Fairless, Ph.D.
/About/Bio
/Projects
/Reposts
/Tags
/Categories
Entries tagged :: efficiency
.
2024-10-30
What I Read: Visual Guide, Quantization
2024-10-28
What I Read: History, Transformer
2024-08-27
What I Read: string ufuncs, NumPy 2.0
2024-07-08
What I Read: Ring Attention
2024-06-17
What I Read: Linear Algebra, Random
2024-06-12
What I Read: Data Selection, LLMs
2024-06-10
What I Read: Mamba Explained
2024-06-05
What I Read: speed up code, Numba
2024-06-04
What I Read: binary vector search
2024-05-14
What I Read: 1-bit LLMs, 1.58 Bits
2024-04-18
What I Read: Scaling ChatGPT, Engineering Challenges
2024-02-21
What I Read: Research Directions
2024-01-16
What I Read: vectorize wide PyTorch expressions
2024-01-10
What I Read: Compiling NumPy
2023-10-24
What I Read: Markov Chains
2023-08-01
What I Read: speed up Numba and NumPy
2023-05-31
What I Read: smaller LLMs, more tokens
2023-05-01
What I Read: Functional, Object Oriented Programming
2023-04-11
What I Learn: neural scaling, data pruning
2023-03-15
What I Read: Optimizing Machine Learning Training Pipelines
2023-01-30
What I Read: Matrix Multiplication
2023-01-11
What I Read: New Chip, AI
2022-08-17
What I Read: Pandas Anti-Patterns
2022-05-10
What I Read: Generalization of SGD
2022-05-09
What I Read: Machine Learning, Building Blocks of Computing
2022-02-23
What I Read: How Should Organizations Structure their Data?
2022-02-22
What I Read: MCMC for big datasets
2021-12-29
What I Read: Model Ensembles Are Faster
2021-12-08
What I Read: True Stories of Algorithmic Improvement
2021-11-08
What I Read: How Train Large Deep Learning Models
2021-07-29
What I Read: Representation quality, complexity
2021-07-28
What I Read: Parallelizing neural networks, GPU, JAX
2021-06-17
What I Read: Make Python Code Fast
2021-05-24
What I Read: Parallel Bayesian Optimization
2021-04-24
What I Read: Deep Learning Recommendation Models
2021-04-09
What I Read: New Algorithm, Linear Equations
2021-03-10
What I Read: Why I’m lukewarm on graph neural networks
2021-03-05
What I Read: Data-efficient image Transformers
2021-02-07
What I Read: Attention with Performers
2021-02-04
What I Read: “Less than one”-shot learning
2021-01-28
What I Read: Sparse Gaussian Processes with Spherical Harmonic Features
2020-12-19
What I Read: sub-linear deep learning algorithm
