📰 Dev.to · Alankrit Verma
7 articles · Updated every 3 hours · View all reads
All
Articles 92,463Blog Posts 110,488Tech Tutorials 23,238Research Papers 19,242News 14,919
⚡ AI Lessons
Dev.to · Alankrit Verma
1mo ago
The Last Pivot: Why Quality Gates Killed My Final KV-Cache Speedup
I wanted to answer one question: After packed-codebook TurboQuant failed, was there still a...
Dev.to · Alankrit Verma
1mo ago
Beating Eager TurboQuant Was Not Enough: Why Dense GPU Attention Still Won
I wanted to answer one question: If I remove eager overhead, can a TurboQuant-style compressed...
Dev.to · Alankrit Verma
1mo ago
When A Good Approximation Still Loses
This is Part 2 of a two-part technical write-up. Part 1 ended with the key architecture lesson: A...
Dev.to · Alankrit Verma
🧠 Large Language Models
⚡ AI Lesson
1mo ago
A Smaller KV Cache Did Not Make Transformers Faster
Long-context generation makes the KV cache hard to ignore. Every generated token reuses keys and...
Dev.to · Alankrit Verma
2mo ago
Synthetic Population Testing for Recommendation Systems
Offline evaluation is necessary for recommender systems. It is also not a full test of recommender...
Dev.to · Alankrit Verma
2mo ago
Why Offline Evaluation Is Not Enough for Recommendation Systems?
Why Offline Evaluation Is Not Enough for Recommendation Systems Offline evaluation is...
Dev.to · Alankrit Verma
3mo ago
How GenAI Genesis Began
TL;DR Alankrit Verma came to the University of Toronto as a shy, math-driven student on scholarship...
DeepCamp AI