Add the support for the qwen3 next model (a hybrid attention model). (#24526)

Signed-off-by: Tao He <linzhu.ht@alibaba-inc.com> Co-authored-by: Jee Jee Li <pandaleefree@gmail.com>
2025-09-11 15:32:09 +08:00
parent 2048c4e379
commit e93f4cc9e3
29 changed files with 2476 additions and 61 deletions
--- a/vllm/config/compilation.py
+++ b/vllm/config/compilation.py
@@ -341,6 +341,7 @@ class CompilationConfig:
        "vllm.short_conv",
        "vllm.linear_attention",
        "vllm.plamo2_mamba_mixer",
+        "vllm.gdn_attention",
    ]

    def compute_hash(self) -> str: