max_model_len

Maximum sequence length, including prompt and output tokens, used by vLLM configuration and scheduler validation.

SettingvLLM v0.23.0verified Jul 9

Claims (0)

No claims about this entity yet.

Availability

max_model_len is exposed on SchedulerConfig in the v0.23.0 source snapshot. The parameter is an InitVar stored on ModelConfig, used by SchedulerConfig for fallbacks and validation.

vllm.config.scheduler_configcomplete_inventorySchedulerConfig InitVar constructor parameter in vllm/config/scheduler.py

vLLM v0.23.0 config scheduler.py · vllm/config/scheduler.py:29-33