Daily Dose of Data Science

Daily Dose of Data Science

LLMs

7 MoE routing strategies in production, clearly explained
+ a practical learning checklist to learn AI engineering.
Nov 7 • Avi Chawla
Why Temperature 0 Isn't Deterministic in LLM Inference
...explained visually (a popular LLM interview question).
Oct 26 • Avi Chawla
Karpathy’s Trick for Faster Local LLMs Finally Has Proper Tooling
Full engineering guide, explained with code.
Oct 8 • Avi Chawla
Chunked Prefill, clearly explained
How vLLM stops one long prompt from stalling others...
Oct 7 • Akshay Pachaar
System 1 vs. System 2 Agent Harnesses, clearly explained
...and a popular MoE interview question.
Sep 28 • Avi Chawla
Contrastive Language Model, clearly explained
NVIDIA and Stanford just challenged Jev...
Sep 25 • Akshay Pachaar
MoE inference engineering, clearly explained
...with visuals.
Sep 23 • Avi Chawla
Build your own Jev (100% local)
...explained step-by-step with code.
Sep 22 • Avi Chawla
Jev, Clearly Explained
...with visuals.
Sep 21 • Avi Chawla
LLM Routing Can Cost More Than Not Routing
...covered with a production-grade router for LLM apps.
Sep 7 • Avi Chawla
5 Embedding Compression Techniques
...explained visually.
Sep 4 • Avi Chawla
Attention Mechanisms in LLMs, clearly explained
Everything you need to understand how attention works, why the KV cache is the bottleneck, and what every attention variant is actually solving.
Sep 3 • Avi Chawla
© 2026 Avi Chawla · Privacy ∙ Terms ∙ Collection notice
Start your SubstackGet the app
Substack is the home for writing, podcasting, and media founders.