Packages

vLLM for Elixir via SnakeBridge - Easy, fast, and cheap LLM serving for everyone. High-throughput LLM inference with PagedAttention, continuous batching, and OpenAI-compatible API.

Current section

Files

Jump to
vllm lib snakebridge_generated vllm.ex
Raw

lib/snakebridge_generated/vllm.ex

# Generated by SnakeBridge v0.8.1 - DO NOT EDIT MANUALLY
# Regenerate with: mix compile
# Library: vllm 0.13.0
defmodule Vllm do
@moduledoc """
SnakeBridge bindings for `vllm`.
## Runtime Options
All functions accept a `__runtime__` option for controlling execution behavior:
Elixir.Vllm.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
### 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
Elixir.Vllm.predict(data, __runtime__: [timeout_profile: :ml_inference])
# Or explicit timeout
Elixir.Vllm.predict(data, __runtime__: [timeout: 600_000])
See `SnakeBridge.Defaults` for global timeout configuration.
"""
def __snakebridge_python_name__, do: "vllm"
def __snakebridge_library__, do: "vllm"
@doc false
def __functions__ do
[]
end
@doc false
def __classes__ do
[]
end
@doc false
def __search__(query) do
SnakeBridge.Docs.search(__MODULE__, query)
end
@doc false
def doc(function) do
SnakeBridge.Docs.get(__MODULE__, function)
end
end