Neural Chronicles2026
Where Asimov's futuristic visions and my learning journey inspire thoughts on real-world engineering and AI — from the perspective of a startup CTO and cofounder.
Featured
Jun 24, 2026
Reading a vLLM Startup Log: A Field Guide to LLM Inference Concepts
A line-by-line tour of a real vLLM cold-start log for Gemma 4, using each phase to explain the core dimensions of LLM inference—context windows, KV cache, FP8 quantization, torch.compile, and CUDA graphs.
AILLMInference
Read articleterminal — bash
Transmission
“The saddest aspect of life right now is that science gathers knowledge faster than society gathers wisdom.”— Isaac Asimov
Neural ActivityLIVE
System Status
Posts
14Projects
ActiveUptime
OnlineProgram status:ACTIVE
Recent postsView all
ArticleAILLM
LLM Landscape 2026: Intelligence Leaderboard and Model Guide
Jun 3, 2026Updated
ArticleAlgorithmsData Structures
Fractional Indexing Algorithm
Apr 1, 2026Updated
ArticleAIDevelopment
My AI-Powered Coding Workflow: From Design to Deployment
Mar 30, 2026Updated
ArticleAIArchitecture
The AI Periodic Table: A Design Language for AI Workflows
Mar 28, 2026
ArticleAILocal Inference
Local Inference Without RAM Limits: How Hypura Streams 70B Models from NVMe
Mar 24, 2026
ArticleAIComputer Science
Is Your AI Hitting a Mathematical Speed Limit?
Jan 24, 2026
Startup modules
Practical guidance and workflow notes for builders — same destinations as before, restyled for the grid.