> ## Documentation Index
> Fetch the complete documentation index at: https://docs.getimpala.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Impala Leap

> Impala Leap swaps model weights in seconds, with no redeploy. Upload a checkpoint, reload it, and the running fleet serves it.

**Impala Leap** changes the weights a running deployment serves, in seconds, without a redeploy. You upload a checkpoint, trigger a reload, and the fleet starts serving the new weights on the same endpoint, through the same engine ([Impala Herd](/impala-herd)).

Use Leap when you retrain or fine-tune on your own cadence and need the serving fleet to follow — RL loops, post-training iteration, or any workflow where new weights ship more often than new infrastructure.

## Endpoints

Impala splits inference from management. Inference runs on the OpenAI-compatible surface; Leap is an Impala-specific operation and lives under `/imp/v1`.

| Method | Path                     | Purpose                                   |
| ------ | ------------------------ | ----------------------------------------- |
| `POST` | `/imp/v1/weights/upload` | Stage a checkpoint from your S3 bucket    |
| `POST` | `/imp/v1/weights/reload` | Swap the staged checkpoint onto the fleet |
| `GET`  | `/imp/v1/weights/status` | Current state of the sync                 |

Base URL: `https://inference.getimpala.ai`. The OpenAI-compatible endpoints sit alongside at `/open-ai/v1/`.

Authentication is the same bearer token you use for inference.

## How a sync progresses

<Frame>
  <img src="https://mintcdn.com/impalaai/D6PXSk0MrZyYwOiY/weight-sync-api.png?fit=max&auto=format&n=D6PXSk0MrZyYwOiY&q=85&s=3bfaa91301c9bed68402df43f2db3bb4" alt="Weight sync API state machine: Ready, POST /upload to Uploading weights, POST /reload to Reloading weights, then new weights live and back to Ready. GET /status is readable throughout." width="2368" height="1326" data-path="weight-sync-api.png" />
</Frame>

`GET /imp/v1/weights/status` is valid at any point and reports which state the fleet is in.

**Ready** — serving current weights, nothing in flight.
**Uploading weights** — the checkpoint is transferring from your bucket. Serving continues on the old weights.
**Reloading weights** — engines are swapping to the new checkpoint.
**Back to Ready** — the new weights are live.

Upload is the long step and scales with checkpoint size and available bandwidth. The reload itself is fast by comparison.

## Uploading a checkpoint

Both `upload` and `reload` take a map of model identifier to S3 URI, so a fleet serving more than one model can be updated per model.

```bash theme={null}
curl -X POST https://inference.getimpala.ai/imp/v1/weights/upload \
  -H "Authorization: Bearer $IMPALA_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "weights": {
      "<model-serve-name>": "s3://your-bucket/checkpoints/2026-08-20/"
    }
  }'
```

Poll until the upload completes:

```bash theme={null}
curl https://inference.getimpala.ai/imp/v1/weights/status \
  -H "Authorization: Bearer $IMPALA_API_KEY"
```

## Reloading

```bash theme={null}
curl -X POST https://inference.getimpala.ai/imp/v1/weights/reload \
  -H "Authorization: Bearer $IMPALA_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "weights": {
      "<model-serve-name>": "s3://your-bucket/checkpoints/2026-08-20/"
    }
  }'
```

Poll `/status` until the fleet returns to `Ready`, then send a test request through your normal inference endpoint to confirm the new weights are answering.

## Things to know

**The checkpoint has to be loadable onto the running engines.** A checkpoint whose architecture or quantization differs from what the fleet is serving cannot be hot-swapped; it needs a new deployment. Impala validates this from the checkpoint's `safetensors` metadata before reloading.

**Failed steps retry automatically**, up to three attempts, before the sync is reported as failed.

**Give Impala read access to the bucket** holding your checkpoints before your first sync.

## Need help?

Reach out to your Impala contact directly.