[BugFix]Fix ep size (#3092)

* fix ep

* fix num_layer
This commit is contained in:
YuanRisheng
2025-07-30 21:03:12 +08:00
committed by GitHub
parent d17886de19
commit 7dfdd157ac
4 changed files with 10 additions and 1 deletions

View File

@@ -1082,6 +1082,7 @@ class LLMEngine:
f" --splitwise_role {self.cfg.splitwise_role}"
f" --kv_cache_ratio {self.cfg.cache_config.kv_cache_ratio}"
f" --expert_parallel_size {self.cfg.parallel_config.expert_parallel_size}"
f" --data_parallel_size {self.cfg.parallel_config.data_parallel_size}"
f" --quantization {self.cfg.model_config.quantization}"
f" --ori_vocab_size {ori_vocab_size}"
f" --speculative_config '{self.cfg.speculative_config.to_json_string()}'"