> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://docs.nvidia.com/nemo/automodel/llms.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.nvidia.com/nemo/automodel/_mcp/server.

# nemo_automodel.components.speculative.eagle.remote

Train-inference disaggregation for EAGLE-3 target serving.

Runs the frozen target model as a standalone inference server on separate
GPU(s) while the draft model trains elsewhere. The training side talks to the
server through :class:`RemoteEagle3TargetModel`, which implements the
:class:`~nemo_automodel.components.speculative.eagle.backend.Eagle3TargetBackend`
contract, so the EAGLE-3 recipe consumes a remote target exactly like the
co-located `HFEagle3TargetModel`.

* HTTP is the control plane (input\_ids up, tensor metadata down).
* NCCL is the data plane for the large supervision tensors (GPU-to-GPU,
  NVLink intra-node / RDMA inter-node), with a compact binary wire format
  fallback when NCCL is unavailable.

## Submodules

* **[`nemo_automodel.components.speculative.eagle.remote.client`](/nemo-automodel/nemo_automodel/components/speculative/eagle/remote/client)**
* **[`nemo_automodel.components.speculative.eagle.remote.protocol`](/nemo-automodel/nemo_automodel/components/speculative/eagle/remote/protocol)**
* **[`nemo_automodel.components.speculative.eagle.remote.server`](/nemo-automodel/nemo_automodel/components/speculative/eagle/remote/server)**
* **[`nemo_automodel.components.speculative.eagle.remote.transport`](/nemo-automodel/nemo_automodel/components/speculative/eagle/remote/transport)**
* **[`nemo_automodel.components.speculative.eagle.remote.wire`](/nemo-automodel/nemo_automodel/components/speculative/eagle/remote/wire)**

## Package Contents

### Data

[`__all__`](#nemo_automodel-components-speculative-eagle-remote-__all__)

### API

```python
nemo_automodel.components.speculative.eagle.remote.__all__ = ['RemoteEagle3TargetModel']
```