The fix was swapping a 4B draft model for a 0.6B one in my speculative decoding config. That's the...
I Fixed My LLM OOM Crashes by Shrinking the Draft Model (Speculative Decoding on Real Hardware)
Related
The Death of "Just Write the Code": How AI-Native Development Is Reshaping What It Means to Be a Developer
You're not losing your job to AI. But the developer who knows how to work with AI might. I used...
AI fixed how fast I can build. It broke how I know what I'm building.
A markdown convention I wrote to track 5-10 half-built projects without losing my mind, and without...
my apps were invisible to AI agents — here's what I am doing about it
i'm an indie app builder and vibe coder. i've shipped over 30 small business apps — invoicing,...