6e00aed4d5
It comes from 0.9.1dev
[0.9.1][Feature]Moe alltoallv communication optimization for unquantized
RL training sence & alltoallv support dpo (#1547)
- vLLM version: v0.10.0
- vLLM main:
97608dc276
---------
Signed-off-by: weijinqian_v1 <weijinqian@huawei.com>
Signed-off-by: whx-sjtu <2952154980@qq.com>
Signed-off-by: curryliu <120010041@link.cuhk.edu.cn>
Signed-off-by: wangli <wangli858794774@gmail.com>
Signed-off-by: ChenTaoyu-SJTU <ctynb@qq.com>
Signed-off-by: taoxudonghaha <justsheldon@163.com>
Signed-off-by: shen-shanshan <467638484@qq.com>
Signed-off-by: Shanshan Shen <87969357+shen-shanshan@users.noreply.github.com>
Signed-off-by: leo-pony <nengjunma@outlook.com>
Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>
Signed-off-by: MengqingCao <cmq0113@163.com>
Co-authored-by: weijinqian_v1 <weijinqian@huawei.com>
Co-authored-by: whx <56632993+whx-sjtu@users.noreply.github.com>
Co-authored-by: curryliu <99582471+Irving11-BKN@users.noreply.github.com>
Co-authored-by: Li Wang <wangli858794774@gmail.com>
Co-authored-by: TaoYu Chen <ctynb@qq.com>
Co-authored-by: taoxudonghaha <justsheldon@163.com>
Co-authored-by: Shanshan Shen <467638484@qq.com>
Co-authored-by: leo-pony <nengjunma@outlook.com>
Co-authored-by: wangxiyuan <wangxiyuan1007@gmail.com>
Co-authored-by: Mengqing Cao <cmq0113@163.com>
62 lines
2.3 KiB
Python
62 lines
2.3 KiB
Python
from vllm import ModelRegistry
|
|
|
|
import vllm_ascend.envs as envs
|
|
|
|
|
|
def register_model():
|
|
from .deepseek_dbo import CustomDeepseekDBOForCausalLM # noqa: F401
|
|
from .deepseek_mtp import CustomDeepSeekMTP # noqa: F401
|
|
from .deepseek_v2 import CustomDeepseekV2ForCausalLM # noqa: F401
|
|
from .deepseek_v3 import CustomDeepseekV3ForCausalLM # noqa: F401
|
|
from .qwen2_5_vl import \
|
|
AscendQwen2_5_VLForConditionalGeneration # noqa: F401
|
|
from .qwen2_vl import AscendQwen2VLForConditionalGeneration # noqa: F401
|
|
from .qwen3 import CustomQwen3ForCausalLM # noqa: F401
|
|
|
|
ModelRegistry.register_model(
|
|
"DeepSeekMTPModel",
|
|
"vllm_ascend.models.deepseek_mtp:CustomDeepSeekMTP")
|
|
|
|
ModelRegistry.register_model(
|
|
"Qwen2VLForConditionalGeneration",
|
|
"vllm_ascend.models.qwen2_vl:AscendQwen2VLForConditionalGeneration")
|
|
|
|
if envs.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.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")
|
|
|
|
ModelRegistry.register_model(
|
|
"PanguProMoEForCausalLM",
|
|
"vllm_ascend.models.pangu_moe:PanguProMoEForCausalLM")
|