Videos
4 total
| Thumb | Title | Channel | Status | Published |
|---|---|---|---|---|
|
Agents That Own Their Inference — Du'an Lightfoot & Khaja Omer, Akamai Technologies
Owning agent inference on a dedicated GPU is cheaper and faster than renting API intelligence for steady workloads:... |
AI Engineer | summarized | 2026-10-11 14:00 |
|
Your GPU Isn't Always Faster at AI (Xenolith Engine Explained)
CPU can be faster than GPU for token generation in AI inference, with Xenolith Engine achieving 18.4 tokens per... |
Cloud Codes | summarized | 2026-10-05 13:16 |
|
Autoresearch Made Our Models 3x Faster — Tejas Bhakta, Morph
Auto research, an agentic loop from Andrej Karpathy's framework, can produce GPU kernels that beat hand tuning by up... |
AI Engineer | summarized | 2026-09-26 15:00 |
|
NVIDIA Just Made AI Memory Transferable Between Models (KV Cache Transfer)
NVIDIA's research shows that KV cache, previously thought model-specific, can be transferred between models using a... |
Cloud Codes | summarized | 2026-08-09 16:00 |
Frontier News · by Hyperjump Technology