Resubmit MoE-EP (#2371)

2024-12-06 15:05:21 +08:00
parent 64fceab8af
commit 3d32e4a32c
10 changed files with 1172 additions and 8 deletions
--- a/python/sglang/srt/model_executor/model_runner.py
+++ b/python/sglang/srt/model_executor/model_runner.py
@@ -141,6 +141,7 @@ class ModelRunner:
                "torchao_config": server_args.torchao_config,
                "enable_nan_detection": server_args.enable_nan_detection,
                "enable_dp_attention": server_args.enable_dp_attention,
+                "enable_ep_moe": server_args.enable_ep_moe,
            }
        )