vector – Andrew Fairless, Ph.D.

What I Read: speed up code, Numba

By Andrew Fairless on June 5, 2024April 15, 2024

https://pythonspeed.com/articles/slow-numba The wrong way to speed up your code with Numbaby Itamar Turner-Trauring21 Mar 2024 “If your NumPy-based code is too slow, you can sometimes use Numba to speed itContinue readingWhat I Read: speed up code, Numba

What I Read: binary vector search

By Andrew Fairless on June 4, 2024April 15, 2024

https://blog.pgvecto.rs/my-binary-vector-search-is-better-than-your-fp32-vectors My binary vector search is better than your FP32 vectorsBinary Vector Search: The 30x Memory Reduction Revolution with Preserved AccuracyCe GaoMar 22, 2024 “…binary vector search… shows promise inContinue readingWhat I Read: binary vector search

What I Read: High-Dimensional Variance

By Andrew Fairless on May 22, 2024March 11, 2024

https://gregorygundersen.com/blog/2023/12/09/covariance-matrices/ High-Dimensional VarianceGregory Gundersen09 December 2023 “A useful view of a covariance matrix is that it is a natural generalization of variance to higher dimensions.”

What I Read: text embeddings

By Andrew Fairless on May 20, 2024March 11, 2024

https://thegradient.pub/text-embedding-inversion/ Do text embeddings perfectly encode text?Jack Morris05.Mar.2024 “What if someone hacks into the database and gains access to all your text embedding vectors – would this be bad?….Put simply:Continue readingWhat I Read: text embeddings

What I Read: survey LLM tooling

By Andrew Fairless on February 8, 2024February 5, 2024

https://ericmjl.github.io/blog/2024/2/1/an-incomplete-and-opinionated-survey-of-llm-tooling/ An (incomplete and opinionated) survey of LLM toolingEric J. Ma1/31/24 7:00 PM “More critical than specifying specific tools, my goal with this blog post is to outline a frameworkContinue readingWhat I Read: survey LLM tooling

What I Read: vectorize wide PyTorch expressions

By Andrew Fairless on January 16, 2024November 7, 2023

https://probablymarcus.com/blocks/2023/10/19/vectorizing-wide-pytorch-expressions.html What happens when you vectorize wide PyTorch expressions?Marcus Lewis19 October 2023 “So we see that vectorization has three effects:It lets us keep the GPU busy even when inputs areContinue readingWhat I Read: vectorize wide PyTorch expressions

What I Read: Compiling NumPy

By Andrew Fairless on January 10, 2024November 7, 2023

https://pytorch.org/blog/compiling-numpy-code/ Compiling NumPy code into C++ or CUDA via torch.compileby Evgeni Burovski, Ralf Gommers and Mario LezcanoOctober 17, 2023 “This feature leverages PyTorch’s compiler to generate efficient fused vectorized codeContinue readingWhat I Read: Compiling NumPy

What I Read: Visualizing Matrix Multiplication

By Andrew Fairless on November 30, 2023October 5, 2023

https://pytorch.org/blog/inside-the-matrix/ Inside the Matrix: Visualizing Matrix Multiplication, Attention and Beyondby Team PyTorchSeptember 25, 2023 “Matrix multiplications (matmuls) are the building blocks of today’s ML models. This note presents mm, aContinue readingWhat I Read: Visualizing Matrix Multiplication

What I Read: To Understand Transformers, Focus on Attention

By Andrew Fairless on October 16, 2023September 4, 2023

https://drscotthawley.github.io/blog/posts/Transformers1-Attention.html To Understand Transformers, Focus on AttentionScott H. HawleyAugust 21, 2023 “To Understand Transformers, Focus on Attention”

What I Read: Multimodal, Embeddings

By Andrew Fairless on October 5, 2023September 4, 2023

https://app.twelvelabs.io/blog/multimodal-embeddings The Multimodal Evolution of Vector EmbeddingsJames LeAugust 9, 2023 “…companies collect and feed hundreds of millions of terabytes of multimodal data into deep learning models. As a result, embeddings…Continue readingWhat I Read: Multimodal, Embeddings

Tag: vector