[MODEL] Adding Support for Qwen3.5 Models (#34110)

Signed-off-by: JJJYmmm <1650675829@qq.com>
Signed-off-by: JJJYmmm <92386084+JJJYmmm@users.noreply.github.com>
Signed-off-by: Roger Wang <hey@rogerw.io>
Co-authored-by: wulipc <wulipc@users.noreply.github.com>
Co-authored-by: ywang96 <ywang96@users.noreply.github.com>
Co-authored-by: Isotr0py <Isotr0py@users.noreply.github.com>
Co-authored-by: Isotr0py <2037008807@qq.com>
Co-authored-by: Roger Wang <hey@rogerw.io>
This commit is contained in:
JJJYmmm
2026-02-09 21:12:58 +08:00
committed by GitHub
co-authored by wulipc ywang96 Isotr0py Isotr0py Roger Wang
parent 9bdb06b436
commit 9562912cea
11 changed files with 1501 additions and 9 deletions
@@ -420,6 +420,11 @@ class Qwen3NextMTPModelArchConfigConvertor(ModelArchConfigConvertorBase):
return getattr(self.hf_text_config, "num_nextn_predict_layers", 0)
class Qwen3_5MTPModelArchConfigConvertor(ModelArchConfigConvertorBase):
def get_num_hidden_layers(self) -> int:
return getattr(self.hf_text_config, "mtp_num_hidden_layers", 0)
class PanguUltraMoeMTPModelArchConfigConvertor(ModelArchConfigConvertorBase):
def get_num_hidden_layers(self) -> int:
return getattr(self.hf_text_config, "num_nextn_predict_layers", 0)
@@ -445,6 +450,7 @@ MODEL_ARCH_CONFIG_CONVERTORS = {
"nemotron-nas": NemotronNasModelArchConfigConvertor,
"deepseek_mtp": DeepSeekMTPModelArchConfigConvertor,
"qwen3_next_mtp": Qwen3NextMTPModelArchConfigConvertor,
"qwen3_5_mtp": Qwen3_5MTPModelArchConfigConvertor,
"mimo_mtp": MimoMTPModelArchConfigConvertor,
"glm4_moe_mtp": GLM4MoeMTPModelArchConfigConvertor,
"glm_ocr_mtp": GLM4MoeMTPModelArchConfigConvertor,