> For clean Markdown content of this page, append .md to this URL. For the complete documentation index, see https://docs.nvidia.com/dynamo/llms.txt. For full content including API reference and SDK examples, see https://docs.nvidia.com/dynamo/llms-full.txt.

# Python API

Dynamo publishes 11 Python modules with 369 public class and function symbols under `dynamo.*`.

#### [dynamo.\_core](python/_core)

97 symbols. Rust-backed distributed runtime, KV router, and endpoint bindings.

#### [dynamo.runtime](python/runtime)

17 symbols. Decorators and re-exports for defining Dynamo workers and endpoints.

#### [dynamo.llm](python/llm)

46 symbols. High-level LLM primitives for building request pipelines.

#### [dynamo.frontend](python/frontend)

43 symbols. OpenAI-compatible HTTP frontend, argument parsing, and pre/post-processing.

#### [dynamo.common](python/common)

77 symbols. Shared configuration groups, storage adapters, and utility helpers.

#### [dynamo.health\_check](python/health_check)

2 symbols. Health-check payload types and environment-driven configuration.

#### [dynamo.logits\_processing](python/logits_processing)

4 symbols. Custom logits processors for LLM token generation.

#### [dynamo.planner](python/planner)

31 symbols. Scaling connectors, decision types, and Planner configuration.

#### [dynamo.router](python/router)

5 symbols. Request-router configuration and command-line argument groups.

#### [dynamo.mocker](python/mocker)

30 symbols. Mock engine used to run Dynamo workflows without a real GPU backend.

#### [dynamo.nixl\_connect](python/nixl_connect)

17 symbols. NIXL RDMA connector primitives for KV cache and tensor transport.

> Public Python surfaces on the Dynamo distributed runtime, statically discovered from the source tree.

## Docs

- [dynamo._core](https://docs.nvidia.com/dynamo/v1.4.0/reference/api/python/_core.md): Rust-backed distributed runtime, KV router, and endpoint bindings.
- [dynamo.runtime](https://docs.nvidia.com/dynamo/v1.4.0/reference/api/python/runtime.md): Decorators and re-exports for defining Dynamo workers and endpoints.
- [dynamo.llm](https://docs.nvidia.com/dynamo/v1.4.0/reference/api/python/llm.md): High-level LLM primitives for building request pipelines.
- [dynamo.frontend](https://docs.nvidia.com/dynamo/v1.4.0/reference/api/python/frontend.md): OpenAI-compatible HTTP frontend, argument parsing, and pre/post-processing.
- [dynamo.common](https://docs.nvidia.com/dynamo/v1.4.0/reference/api/python/common.md): Shared configuration groups, storage adapters, and utility helpers.
- [dynamo.health_check](https://docs.nvidia.com/dynamo/v1.4.0/reference/api/python/health_check.md): Health-check payload types and environment-driven configuration.
- [dynamo.logits_processing](https://docs.nvidia.com/dynamo/v1.4.0/reference/api/python/logits_processing.md): Custom logits processors for LLM token generation.
- [dynamo.planner](https://docs.nvidia.com/dynamo/v1.4.0/reference/api/python/planner.md): Scaling connectors, decision types, and Planner configuration.
- [dynamo.router](https://docs.nvidia.com/dynamo/v1.4.0/reference/api/python/router.md): Request-router configuration and command-line argument groups.
- [dynamo.mocker](https://docs.nvidia.com/dynamo/v1.4.0/reference/api/python/mocker.md): Mock engine used to run Dynamo workflows without a real GPU backend.
- [dynamo.nixl_connect](https://docs.nvidia.com/dynamo/v1.4.0/reference/api/python/nixl_connect.md): NIXL RDMA connector primitives for KV cache and tensor transport.