[model] Add mamba2 and Falcon-H1 support. (#10988)

Co-authored-by: Younes Belkada <younes.belkada@tii.ae> Co-authored-by: Younes B <49240599+younesbelkada@users.noreply.github.com>
2025-10-02 15:15:36 +04:00
parent b658be6f6a
commit 083629c235
18 changed files with 4533 additions and 1 deletions
--- a/python/sglang/srt/model_executor/model_runner.py
+++ b/python/sglang/srt/model_executor/model_runner.py
@@ -1297,6 +1297,7 @@ class ModelRunner:
        return self.model_config.hf_config.architectures[0] in [
            "Qwen3NextForCausalLM",
            "Qwen3NextForCausalLMMTP",
+            "FalconH1ForCausalLM",
        ]

    def set_num_token_hybrid(self):