Matt Cool's picture

2 3

Matt Cool

mbcool

·

https://mattcool.tech/

AI & ML interests

Open Source, local and offline.

Recent Activity

liked a Space about 16 hours ago

nvidia/nemotron-speech-streaming-en-0.6b

commented on an article 7 months ago

KV Caching Explained: Optimizing Transformer Inference Efficiency

upvoted an article 7 months ago

KV Caching Explained: Optimizing Transformer Inference Efficiency

View all activity

Organizations

liked a Space about 16 hours ago

Nemotron Speech Streaming

Real-time speech recognition with NVIDIA Triton

liked 2 models over 1 year ago

mozilla-ai/Meta-Llama-3.1-8B-Instruct-llamafile

Updated Mar 31, 2025 • 1.55k • 42

mozilla-ai/Mistral-7B-Instruct-v0.2-llamafile

Text Generation • 7B • Updated May 25, 2024 • 5.29k • 25