dynamo-mocker
dynamo-mocker is a GPU-free simulation crate for Dynamo's LLM scheduling and KV-cache behavior.
It is used for testing, replay, and benchmarking workflows where you want realistic scheduler and
cache behavior without running a real inference engine.
What This Crate Provides
MockEngineArgsfor configuring a simulated engineengine::create_enginefor building a vLLM-style or SGLang-style mock schedulerKvEventPublishershooks for emitting router-visible KV cache eventsloadgenandreplaymodules for synthetic and trace-driven experiments
Basic Rust Usage
use ;
use create_engine;
let args = builder
.block_size
.num_gpu_blocks
.max_num_seqs
.max_num_batched_tokens
.build
.unwrap;
let engine = create_engine;
engine.receive;
This crate is also the foundation for Dynamo's higher-level mocker CLI and replay tooling. In many deployments you will interact with it indirectly through the Python entry points rather than embedding it directly as a standalone Rust dependency.
Further Reading
- Mocker guide: ../../docs/fern/dynosim/mocker.mdx
- DynoSim runs guide: ../../docs/fern/dynosim/runs.mdx
- Python component README: ../../components/src/dynamo/mocker/README.md