c556038ef0
### What this PR does / why we need it?
Add Qwen3-next support.
### Does this PR introduce _any_ user-facing change?
Yes, users can use Qwen3 next.
Related doc: https://github.com/vllm-project/vllm-ascend/pull/2916 the
tutorial will be ready in
[here](https://vllm-ascend.readthedocs.io/en/latest/tutorials/multi_npu_qwen3_next.html)
### How was this patch tested?
Doc CI passed
Related: https://github.com/vllm-project/vllm-ascend/issues/2884
Co-Authored-By: Angazenn <supperccell@163.com>
Co-Authored-By: zzzzwwjj <1183291235@qq.com>
Co-Authored-By: MengqingCao <cmq0113@163.com>
Co-Authored-By: linfeng-yuan <1102311262@qq.com>
Co-Authored-By: hust17yixuan <303660421@qq.com>
Co-Authored-By: SunnyLee219 <3294305115@qq.com>
Co-Authored-By: maoxx241 <maoxx241@umn.edu>
- vLLM version: v0.10.2
- vLLM main:
b834b4cbf1
---------
Signed-off-by: MengqingCao <cmq0113@163.com>
Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>
Signed-off-by: Angazenn <supperccell@163.com>
Signed-off-by: Your Name <you@example.com>
Signed-off-by: zzzzwwjj <1183291235@qq.com>
Signed-off-by: linfeng-yuan <1102311262@qq.com>
Signed-off-by: hust17yixuan <303660421@qq.com>
Co-authored-by: MengqingCao <cmq0113@163.com>
Co-authored-by: Angazenn <supperccell@163.com>
Co-authored-by: Your Name <you@example.com>
Co-authored-by: zzzzwwjj <1183291235@qq.com>
Co-authored-by: linfeng-yuan <1102311262@qq.com>
Co-authored-by: hust17yixuan <303660421@qq.com>
59 lines
2.2 KiB
Python
59 lines
2.2 KiB
Python
from vllm import ModelRegistry
|
|
|
|
import vllm_ascend.envs as envs_ascend
|
|
|
|
|
|
def register_model():
|
|
ModelRegistry.register_model(
|
|
"DeepSeekMTPModel",
|
|
"vllm_ascend.models.deepseek_mtp:CustomDeepSeekMTP")
|
|
|
|
ModelRegistry.register_model(
|
|
"Qwen2VLForConditionalGeneration",
|
|
"vllm_ascend.models.qwen2_vl:AscendQwen2VLForConditionalGeneration")
|
|
|
|
if envs_ascend.USE_OPTIMIZED_MODEL:
|
|
ModelRegistry.register_model(
|
|
"Qwen2_5_VLForConditionalGeneration",
|
|
"vllm_ascend.models.qwen2_5_vl:AscendQwen2_5_VLForConditionalGeneration"
|
|
)
|
|
else:
|
|
ModelRegistry.register_model(
|
|
"Qwen2_5_VLForConditionalGeneration",
|
|
"vllm_ascend.models.qwen2_5_vl_without_padding:AscendQwen2_5_VLForConditionalGeneration_Without_Padding"
|
|
)
|
|
|
|
if envs_ascend.VLLM_ASCEND_ENABLE_DBO:
|
|
ModelRegistry.register_model(
|
|
"DeepseekV2ForCausalLM",
|
|
"vllm_ascend.models.deepseek_dbo:CustomDeepseekDBOForCausalLM")
|
|
|
|
ModelRegistry.register_model(
|
|
"DeepseekV3ForCausalLM",
|
|
"vllm_ascend.models.deepseek_dbo:CustomDeepseekDBOForCausalLM")
|
|
else:
|
|
ModelRegistry.register_model(
|
|
"DeepseekV2ForCausalLM",
|
|
"vllm_ascend.models.deepseek_v2:CustomDeepseekV2ForCausalLM")
|
|
|
|
ModelRegistry.register_model(
|
|
"DeepseekV3ForCausalLM",
|
|
"vllm_ascend.models.deepseek_v3:CustomDeepseekV3ForCausalLM")
|
|
|
|
ModelRegistry.register_model(
|
|
"Qwen3MoeForCausalLM",
|
|
"vllm_ascend.models.qwen3_moe:CustomQwen3MoeForCausalLM")
|
|
|
|
ModelRegistry.register_model(
|
|
"Qwen3ForCausalLM", "vllm_ascend.models.qwen3:CustomQwen3ForCausalLM")
|
|
|
|
# There is no PanguProMoEForCausalLM in vLLM, so we should register it before vLLM config initialization
|
|
# to make sure the model can be loaded correctly. This register step can be removed once vLLM support PanguProMoEForCausalLM.
|
|
ModelRegistry.register_model(
|
|
"PanguProMoEForCausalLM",
|
|
"vllm_ascend.torchair.models.torchair_pangu_moe:PanguProMoEForCausalLM"
|
|
)
|
|
ModelRegistry.register_model(
|
|
"Qwen3NextForCausalLM",
|
|
"vllm_ascend.models.qwen3_next:Qwen3NextForCausalLM")
|