This is your work, valued

United Kingdom

Christopher Fleetwood

Elite
@FL33TW00D

Reality is an undefeated champion

whisper-turbo. Cross-Platform, GPU Accelerated Whisper 🏎️

1.8k

laserbeak. Add local LLMs to your Web or Electron apps! Powered by Rust + WebGPU

102

wgpu-mm. WGSL

72

embd. GPU accelerated client-side embeddings for vector search, RAG etc.

65

steelix. Your one stop CLI for ONNX model analysis.

48

deCoreML. Find out why your CoreML model isn't running on the Neural Engine!

30

coremlprofiler. Profile your CoreML models directly from Python 🐍

29

rustDTW. Python extension backed by a multi-threaded Rust implementation of Dynamic Time Warping (DTW).

27

dots.ocr.ne. Python

24

wattkit. Rust

15

wgpu-bench. Rust

12

tokenizers-sys. C bindings for HuggingFace `tokenizers`

7

he-man. Python

7

wgpu. Safe and portable GPU abstraction in Rust, implementing WebGPU API.

7

wasm-boids. A Three.JS + WASM implementation of Boids.

6

wgpu-tensor. Rust

6

swift-tokenizers. Wrapping C `tokenizers` in ergonomic, safe Swift.

5

inline-wgsl. Rust

5

ffmpeg.wasm. FFmpeg for browser, powered by WebAssembly

4

macmon. πŸ¦€βš™οΈ Sudoless performance monitoring for Apple Silicon processors. CPU / GPU / RAM usage, power consumption & temperature 🌑️

3

mlx-conformer. Python

2

FL33TW00D.

2

candle. Minimalist ML framework for Rust

1

segment-anything-2. The repository provides code for running inference with the Meta Segment Anything Model 2 (SAM 2), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.

1

voy. πŸ•ΈοΈπŸ¦€ A WASM vector similarity search written in Rust

1

on-device-transcription. A ready-to-use, minimal app that converts any speech into text.

1

modcomp. Can you compress ML models with traditional compression? Answer: No

1

ane. Reverse engineered Linux driver for the Apple Neural Engine (ANE).

1

whisper.cpp. Port of OpenAI's Whisper model in C/C++

1

tfjs-mm. JavaScript

1

ogs_repro. Python

1

web-ai. Run modern deep learning models in the browser.

1

whisper. Robust Speech Recognition via Large-Scale Weak Supervision

1

onnxruntime. ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator

1

stream_to_asynciter. Rust

1