Inference cost at scale with napkin math (injuly.in) | HN Screenshots

YHacker Newsscreenshots

Screenshot of injuly.in: Inference cost at scale with napkin math

First screen, captured 4 months ago.

Looks similar

Screenshot of damek.github.io: Basic Facts about GPUs

Basic Facts about GPUs (damek.github.io)

306 points by ibobev 1 year ago | 66 comments

Screenshot of siboehm.com: How to optimize a CUDA matmul kernel for cuBLAS-like performance (2022)

How to optimize a CUDA matmul kernel for cuBLAS-like performance (2022)(siboehm.com)

86 points by mpweiher 2 years ago | 21 comments

Screenshot of zeux.io: LLM Inference Speed of Light

LLM Inference Speed of Light (zeux.io)

8 points by ashvardanian 2 years ago | 0 comments

Screenshot of veitner.bearblog.dev: Calculating the Fibonacci numbers on GPU

Calculating the Fibonacci numbers on GPU (veitner.bearblog.dev)

34 points by rbanffy 1 year ago | 20 comments

Screenshot of dkryaklin.com: Converting colors in JavaScript at 6B operations per second

Converting colors in JavaScript at 6B operations per second (dkryaklin.com)

26 points by dkryaklin 3 months ago | 6 comments

Screenshot of ml-explore.github.io: MLX: NumPy like framework for Apple Silicon by Apple

MLX: NumPy like framework for Apple Silicon by Apple (ml-explore.github.io)

131 points by dagmx 2 years ago | 12 comments