gpus
36 talks
Turning My Obsidian Vault Into a Local AI Engineer
From 15% to 90% GPU Utilization: Fix the Data Pipeline, Not the Model
Is Speculative Decoding Worth It? Profiling vLLM on NVIDIA Blackwell
What Is an Inference Engine, Anyway?
GPU Died. Training Didn't: Self-Healing Training at Scale
Lessons from Generating 12 Trillion Synthetic Tokens
Autoresearch Made Our Models 3x Faster
Large clusters for small models
Weight Folding, CUDA Streams, and the Bug That Made My Model Speak Backwards
Can LLMs Write Fast Multi-GPU Kernels?
Infra behind Krea 2: How to train and serve at scale
The Desktop Frontier
Stop Renting Your Cognitive Infrastructure
Road to 5 Million Tokens: Breaking Barriers in Long Context Training
Under 5 minutes to a deployed LLM endpoint
Run Frontier AI at Home
The Small Model Infrastructure Nobody Built (So We Did)
AI Kernel Generation: What's Working, What's Not, What's Next
Efficient Reinforcement Learning
#define AI Engineer
Hacking the Inference Pareto Frontier
Why We Don't Need More Data Centers
Continuous Profiling for GPUs
What Every AI Engineer Needs to Know About GPUs
RL for Autonomous Coding
The Geopolitics of AI Infrastructure
Luminal: Search-Based Deep Learning Compilers
How to Build Your Own AI Data Center in 2025
Accelerating Mixture of Experts Training With Rail-Optimized InfiniBand Networking in Crusoe Cloud
System Design for Next-Gen Frontier Models
Fine-tune 20 Llama Models in 5 Minutes
Insights from Snorkel AI Running Azure AI Infrastructure
Mastering LLM Inference Optimization From Theory to Cost Effective Deployment
From Model Weights to API Endpoint with TensorRT-LLM
Unlocking Developer Productivity across CPU and GPU with MAX
GPUs & Inference Track