Skip to main content

Module profile

Module profile 

Source

Structs§

BenchLimits
BenchResult
Structured output of a single bench run: named metrics (e.g. (“evaltime”, secs), (“pp512”, tok/s)) plus the loop iteration count for the human report line. The bench/llm-bench runners return this so callers — the interactive subcommand or the bench suite — consume data instead of parsing stdout.
Profiler

Functions§

extract_costs
profile
profile_gpu
rec_profiler
rec_profiler_gpu
reusable_state
run_one_step
stage_metrics_from_readings
Extract the load-time readings the bench suite reports from a readings-probe output file. For each tracked checkpoint, emit time_to_<stage> (elapsed seconds), rsz_at_<stage> (resident bytes) and active_at_<stage> (alloc − free bytes). A missing file or absent checkpoint is skipped; the orchestrator decides which metrics are required.