[Loader] add multi-thread model loading (#6877)

* multi-thread-loader * fix ut
2026-04-23 00:17:25 +08:00 · 2026-04-10 14:40:15 +08:00
parent c1fb3112f8
commit 14d46181b8
12 changed files with 105 additions and 7 deletions
@@ -613,6 +613,7 @@ class LLMEngine:
            f" --early_stop_config '{self.cfg.early_stop_config.to_json_string()}'"
            f" --reasoning_parser {self.cfg.structured_outputs_config.reasoning_parser}"
            f" --load_choices {self.cfg.load_config.load_choices}"
+            f" --model_loader_extra_config '{json.dumps(self.cfg.load_config.model_loader_extra_config)}'"
            f" --plas_attention_config '{self.cfg.plas_attention_config.to_json_string()}'"
            f" --ips {ips}"
            f" --max_encoder_cache {self.cfg.cache_config.max_encoder_cache}"