Videos
5 total
| Thumb | Title | Channel | Status | Published |
|---|---|---|---|---|
|
Weight Folding, CUDA Streams, and the Bug That Made My Model Speak Backwards — Filip Makraduli
A paper co-authored by Filip Makraduli proposes two algebraic tricks—weight folding and deferred normalization—that... |
AI Engineer | summarized | 2026-09-19 19:00 |
|
Run a $10,000 AI Model at Home, Here’s How
Open source models have narrowed the capability gap with frontier labs to 3-6 months, with recent releases like Kimi... |
David Ondrej | summarized | 2026-09-09 10:27 |
|
AMD Shipped Skills for Claude, Cursor and Codex (All 8 of Them)
AMD's ROCm 10 release ships a 'skills' folder that teaches Claude, Cursor, and Codex how to use its GPUs,... |
Cloud Codes | summarized | 2026-08-31 09:00 |
|
The KV Cache Layer That Makes LLMs 10x Faster? (LMCache)
The KV cache is the dominant cost in long-context LLM serving, and the built-in prefix caching in frameworks like... |
Cloud Codes | summarized | 2026-08-27 19:30 |
|
Speculative Decoding: The ONLY Video You Need to Speed Up Inference
Speculative decoding is a lossless inference acceleration technique that uses a small draft model to propose... |
Cloud Codes | summarized | 2026-08-26 19:30 |
Frontier News · by Hyperjump Technology