Provide default max model length (#1224)

2023-09-28 14:44:02 -07:00
parent 6f88f762bf
commit f936657eb6
4 changed files with 14 additions and 9 deletions
--- a/vllm/engine/arg_utils.py
+++ b/vllm/engine/arg_utils.py
@@ -184,7 +184,7 @@ class EngineArgs:
                                         self.worker_use_ray)
        scheduler_config = SchedulerConfig(self.max_num_batched_tokens,
                                           self.max_num_seqs,
-                                           model_config.get_max_model_len())
+                                           model_config.max_model_len)
        return model_config, cache_config, parallel_config, scheduler_config