GLM-4.5 Model Support (#8224)

Co-authored-by: Lifu Huang <lifu.hlf@gmail.com> Co-authored-by: Binyao Jiang <byjiang1996@gmail.com> Co-authored-by: Stefan He <hebiaobuaa@gmail.com>
2025-07-28 13:54:07 +08:00
parent 2fd5c7049f
commit 6d6a8bc278
14 changed files with 1673 additions and 7 deletions
--- a/python/sglang/srt/utils.py
+++ b/python/sglang/srt/utils.py
@@ -2343,6 +2343,7 @@ def is_fa3_default_architecture(hf_config):
        "Gemma3ForConditionalGeneration",
        "Qwen3ForCausalLM",
        "Qwen3MoeForCausalLM",
+        "Glm4MoeForCausalLM",
    }
    return architectures[0] in default_archs