Notes from the Tail
Home
Blog
27 Feb, 2026
The Scheduling Reckoning: Deterministic GPU Performance and Orchestration Rewiring
21 Feb, 2026
Model Weights Distribution: The Terabyte Page Fault
10 Feb, 2026
KV-Cache Is the New Heap Allocator: Tail Latency at Scale for LLM Inference
#potofhoney