anansi
benchmark
anansi | benchmark | |
---|---|---|
2 | 3 | |
48 | 789 | |
- | 2.8% | |
4.9 | 9.8 | |
11 months ago | 1 day ago | |
Rust | Python | |
Apache License 2.0 | BSD 3-clause "New" or "Revised" License |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
anansi
-
DiskANN Implementation in Rust + Easy NN Search
Hi! I have been noodling away at a re-implementation of the original C++ DiskANN project as well as packaging the latest advances in embedding generation. The rough repo is here and will remain licensed as Apache-2.0!
- PyTorch Primitives in WebGPU for the Browser
benchmark
-
PyTorch Primitives in WebGPU for the Browser
>What's a fair benchmark?
the absolute golden benchmarks are https://github.com/pytorch/benchmark
- [R] AMD Instinct MI25 | Machine Learning Setup on the Cheap!
-
[R] PyTorch | Budget GPU Benchmarking
TorchBench (https://github.com/pytorch/benchmark) is used by PyTorch core developers to test performance across a wide variety of models. I've never used it personally though.
What are some alternatives?
bionic-gpt - BionicGPT is an on-premise replacement for ChatGPT, offering the advantages of Generative AI while maintaining strict data confidentiality
llama.cpp - LLM inference in C/C++
chidori - A reactive runtime for building durable AI agents
wonnx - A WebGPU-accelerated ONNX inference run-time written 100% in Rust, ready for native and the web
bionicgpt - BionicGPT is an on-premise replacement for ChatGPT, offering the advantages of Generative AI while maintaining strict data confidentiality [Moved to: https://github.com/bionic-gpt/bionic-gpt]
potatogpt - Pure Typescript, dependency free, ridiculously slow implementation of GPT2 for educational purposes
DiskANN - Graph-structured Indices for Scalable, Fast, Fresh and Filtered Approximate Nearest Neighbor Search
opov - Operator Overloading for Typescript with Tagged Template Literals
requests-wasm-polyfill - Drop-in replacement for the requests library for wasm python
shumai - Fast Differentiable Tensor Library in JavaScript and TypeScript with Bun + Flashlight
tfjs - A WebGL accelerated JavaScript library for training and deploying ML models.