sleepyeldrazi | Dark Hacker News

user:	sleepyeldrazi
created:	June 3, 2021
karma:	91
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.

1.	DeepSeek V4 Flash optimized framework and model variants for DGX Spark(github.com) 3 points by sleepyeldrazi 62 days ago \| 1 comment
2.	Ask HN: Local model experiences with 'high-reasoning distill' finetunes 2 points by sleepyeldrazi 91 days ago \| 0 comments