MLX India Community Meetup 1 | Boosting local model performance - Speculative decoding with DFlash
Speculative decoding is a technique to obtain a decoding speedup in LLM inference. Sabesh talks about implementing speculative decoding on MLX using a library called DFlash and about a controlled sweep that was performed right on his MacBook. The findings were documented and published.

▶︎
Loop Engineering explained in 8min..

▶︎
MLX India Community Meetup 1 | Builder Demos

▶︎
Trelis Tiron - State-of-the-Art Multi-speaker Meeting Transcription and Attribution (Open Weights!)

▶︎
Diffusion Language Models, LLaDA, Nemotron-TwoTower and more | Bangalore Paper Club

▶︎
MLX India Community Meetup 1 | The MLX framework 101

▶︎
MLX India Community Meetup 2 | Fine-tuning models using MLX by Sabesh Bharathi

▶︎
The Most Important Conversation in AI Right Now

▶︎
🔴WARNING! Jesus Says: Your Old Life Is Over—A New Beginning Starts Today | God's Message | God Says

▶︎
The Agent Development Lifecycle 101 by Harrison Chase

▶︎
Is RAG Still Needed? Choosing the Best Approach for LLMs

▶︎
ASMR Deep Ear Attention

▶︎
URGENT UPDATE - Iran War Expert: A Mass Casualty Attack Is Coming! | Robert Pape

▶︎
CHOSEN ONE!! YOUR IDENTITY REVEAL JUST SHOOK THE INTERNET... AND THEIR MINDS

▶︎
Everyone's Comparing MCP and API Wrong

▶︎
You Can Learn AI Agent Harness & Loop Engineering In 19 Min | LLM Ops, Eval, Tracing, RAG

▶︎
How To Think SO Clearly People Assume You're Brilliant
![PINK & ORANGE GRADIENT IN HD [3 HOURS]](https://i.ytimg.com/vi/6ih8zppfQSQ/hqdefault.jpg?sqp=-oaymwE9CNACELwBSFryq4qpAy8IARUAAAAAGAElAADIQj0AgKJDeAHwAQH4Af4JgALQBYoCDAgAEAEYfyAsKBMwDw==&rs=AOn4CLDvw6mQM98bfl572zfE7r4GdUG8dg)
▶︎
PINK & ORANGE GRADIENT IN HD [3 HOURS]

▶︎
Stanford MS&E435 Economics of the AI Supercycle | Spring 2026 | Infrasctructure, Enterprise AI, SaaS

▶︎
MCP vs API: Why traditional APIs are failing AI agents

▶︎
