Open Source Static Performance Model for LLM Inference

stanfordnlp · x · 2026-08-29

Inspired by Percy Liang's CS336, the author built a static performance model for LLM inference that provides clean analytical bounds without dynamic batching. Users can select model, GPU, batch size, sequence length, and parallelism strategies (DP/TP/EP/PP) to get VRAM checks, TTFT, TPOT, and throughput breakdowns.

Key features:

Original post →

More from Infra

Infra channel →