subblock_stats

Modules

modelopt.torch.puzzletron.subblock_stats.calc_runtime_stats

Runtime statistics calculation for NAS subblock benchmarking via vLLM.

modelopt.torch.puzzletron.subblock_stats.calc_subblock_params_and_memory

Calculate memory usage and parameter counts for neural network subblocks.

modelopt.torch.puzzletron.subblock_stats.calc_subblock_stats

Calc subblock stats to compute memory and runtime statistics for subblocks.

modelopt.torch.puzzletron.subblock_stats.measurements

Runtime application helpers for named vLLM measurement contracts.

modelopt.torch.puzzletron.subblock_stats.runtime_estimator

Layout and arithmetic primitives for repeated-candidate runtime estimates.

modelopt.torch.puzzletron.subblock_stats.runtime_utils

Utilities for runtime benchmarking and model saving in Puzzletron.

modelopt.torch.puzzletron.subblock_stats.runtime_vllm

vLLM Runtime Benchmark Integration for ModelOpt NAS Subblocks.

modelopt.torch.puzzletron.subblock_stats.topology

Explicit distributed topology for vLLM runtime measurements.

Subblock statistics collection for Puzzletron.