sleepyeldrazi

Karma: 80
Created: 5 years ago

About

Personal projects at https://git.kokoham.com/sleepy . Trying to optimize LLM inference frameworks for local models in speed, and explore interesting quants for size.

Recent Submissions

1. ▲ DeepSeek V4 Flash optimized framework and model variants for DGX Spark (github.com) 3 points · 5 days ago · 1 comment
2. ▲ Ask HN: Local model experiences with 'high-reasoning distill' finetunes 2 points · 1 month ago · 0 comments
3. ▲ The only non-LLM-generated file in my repo (github.com) 2 points · 2 months ago · 1 comment

All submissions on HN · View profile on HN

Settings

sleepyeldrazi

About

Recent Submissions

Keyboard Shortcuts