# `mix llm_core.bench`
[🔗](https://github.com/fosferon/llm_core/blob/v0.3.0/lib/mix/tasks/llm_core.bench.ex#L15)

Runs ALF routing and inference pipeline benchmarks.

Registers a lightweight test provider, configures a routing table pointing at
it, then fires `iterations` calls through the inference pipeline with
configurable parallelism. Reports total time, average latency, and throughput.

## Examples

    mix llm_core.bench
    mix llm_core.bench --iterations 500 --parallel 8
    mix llm_core.bench --mode packet

---

*Consult [api-reference.md](api-reference.md) for complete listing*