Article
Introducing Superfluid: the local-AI native LLM server for multi-agent inference
basecompute
• • 3
Lukas Wesemann
Lukas-bc
AI & ML interests
Building local AI
Recent Activity
upvoted an article 4 days ago
Introducing Superfluid: the local-AI native LLM server for multi-agent inference published an article 4 days ago
Introducing Superfluid: the local-AI native LLM server for multi-agent inference commentedon an article 21 days ago
Compute:Arena / Measuring Local Inference Across Models, Quants, Chips, and RuntimesOrganizations
upvoted an article 4 days ago
published an article 4 days ago
Article
Introducing Superfluid: the local-AI native LLM server for multi-agent inference
basecompute
• • 3 commented on Compute:Arena / Measuring Local Inference Across Models, Quants, Chips, and Runtimes 21 days ago
Let me know if you run into any glitches, we're quick to fix things :)
commented on Compute:Arena / Measuring Local Inference Across Models, Quants, Chips, and Runtimes 21 days ago
Hope you are getting value out of this, more runtimes are being added!
published an article 21 days ago
Article
Compute:Arena / Measuring Local Inference Across Models, Quants, Chips, and Runtimes
basecompute
• • 6 commented on Base Optimization Stack: From Open Weights to Frontier On-Device Inference Speed about 2 months ago
we've shared our recent research results using this stack in two papers : https://www.basecompute.co/research
upvoted an article about 2 months ago
Article
Base Optimization Stack: From Open Weights to Frontier On-Device Inference Speed
basecompute
• • 5 published an article 3 months ago
Article
BaseRT: Best-in-Class LLM Inference on Apple Silicon via Native Metal
basecompute
• • 5 updated a
Space 4 months ago
published a
Space 4 months ago