# `Vllm.ModelExecutor.Models.Interfaces`
[🔗](https://github.com/nshkrdotcom/vllm/blob/v0.3.0/lib/snakebridge_generated/vllm/model_executor/models/interfaces/__init__.ex#L6)

Submodule bindings for `vllm.model_executor.models.interfaces`.

## Version

- Requested: 0.14.0
- Observed at generation: 0.14.0

## Runtime Options

All functions accept a `__runtime__` option for controlling execution behavior:

    Vllm.ModelExecutor.Models.Interfaces.some_function(args, __runtime__: [timeout: 120_000])

### Supported runtime options

- `:timeout` - Call timeout in milliseconds (default: 120,000ms / 2 minutes)
- `:timeout_profile` - Use a named profile (`:default`, `:ml_inference`, `:batch_job`, `:streaming`)
- `:stream_timeout` - Timeout for streaming operations (default: 1,800,000ms / 30 minutes)
- `:session_id` - Override the session ID for this call
- `:pool_name` - Target a specific Snakepit pool (multi-pool setups)
- `:affinity` - Override session affinity (`:hint`, `:strict_queue`, `:strict_fail_fast`)

### Timeout Profiles

- `:default` - 2 minute timeout for regular calls
- `:ml_inference` - 10 minute timeout for ML/LLM workloads
- `:batch_job` - Unlimited timeout for long-running jobs
- `:streaming` - 2 minute timeout, 30 minute stream_timeout

### Example with timeout override

    # For a long-running ML inference call
    Vllm.ModelExecutor.Models.Interfaces.predict(data, __runtime__: [timeout_profile: :ml_inference])

    # Or explicit timeout
    Vllm.ModelExecutor.Models.Interfaces.predict(data, __runtime__: [timeout: 600_000])

    # Route to a pool and enforce strict affinity
    Vllm.ModelExecutor.Models.Interfaces.predict(data, __runtime__: [pool_name: :strict_pool, affinity: :strict_queue])

See `SnakeBridge.Defaults` for global timeout configuration.

---

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