vLLM: a high-throughput and memory-efficient inference engine for LLMs
Version
- Requested: 0.14.0
- Observed at generation: 0.14.0
Runtime Options
All functions accept a __runtime__ option for controlling execution behavior:
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: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.predict(data, __runtime__: [timeout_profile: :ml_inference])
# Or explicit timeout
Vllm.predict(data, __runtime__: [timeout: 600_000])
# Route to a pool and enforce strict affinity
Vllm.predict(data, __runtime__: [pool_name: :strict_pool, affinity: :strict_queue])See SnakeBridge.Defaults for global timeout configuration.