API Reference

Core API

Primary objects and solvers.

hardware
models
infra
systems
core
core.solver.SingleNodeModel	Resolves single-node hardware Roofline bounds and feasibility.
core.solver.ServingModel	Analyzes the two-phase LLM serving lifecycle: Pre-fill vs. Decoding.
core.solver.DistributedModel	Resolves fleet-wide communication, synchronization, and pipelining constraints.
core.solver.DataModel	Analyzes the ‘Data Wall’ — the throughput bottleneck between storage and compute.
core.solver.ScalingModel	Analyzes the ‘Scaling Physics’ of model training (Chinchilla Laws).
core.solver.OrchestrationModel	Analyzes Cluster Orchestration and Queueing (Little’s Law).
core.solver.CompressionModel	Analyzes model compression trade-offs (Accuracy vs. Efficiency).
core.solver.SustainabilityModel	Calculates Datacenter-scale Sustainability metrics.
core.solver.EconomicsModel	Calculates Total Cost of Ownership (TCO) including Capex and Opex.
core.solver.ContinuousBatchingModel	Analyzes production LLM serving with Continuous Batching and PagedAttention.
core.solver.WeightStreamingModel	Analyzes Wafer-Scale inference (e.g., Cerebras CS-3) using Weight Streaming.
core.solver.TailLatencyModel	Analyzes queueing delays and P99 tail latency for deployed inference (M/M/c).
core.solver.ReliabilityModel	Calculates Mean Time Between Failures (MTBF) and optimal checkpointing intervals.
core.solver.CheckpointModel	Analyzes checkpoint I/O burst penalties and MFU impact.