[Core] Refactor model loading code (#4097)

2024-04-16 11:34:39 -07:00
parent 05434764cd
commit 69e1d2fb69
67 changed files with 1054 additions and 963 deletions
--- a/tests/spec_decode/utils.py
+++ b/tests/spec_decode/utils.py
@@ -118,6 +118,7 @@ def create_worker(cls: type,
        scheduler_config=engine_config.scheduler_config,
        device_config=engine_config.device_config,
        cache_config=engine_config.cache_config,
+        load_config=engine_config.load_config,
        local_rank=0,
        rank=0,
        distributed_init_method=distributed_init_method,