81bd6e4c99
### What this PR does / why we need it? This PR added the initial DeepSeek V3.2 support with [vLLM v0.11.0](https://github.com/vllm-project/vllm/tree/releases/v0.11.0) (not released yet). We will complete vLLM adaptation as soon as possible. This feature will be ready in recent 1-2 days. Related doc: https://github.com/vllm-project/vllm-ascend/pull/3223 . ### Does this PR introduce _any_ user-facing change? Yes! ### How was this patch tested? CI passed and Run deepseek doc soon. - vLLM version: v0.11.0rc3 - vLLM main: https://github.com/vllm-project/vllm/commit/releases/v0.11.0 --------- Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com> Signed-off-by: zzzzwwjj <1183291235@qq.com> Signed-off-by: linfeng-yuan <1102311262@qq.com> Signed-off-by: wxsIcey <1790571317@qq.com> Signed-off-by: MengqingCao <cmq0113@163.com> Co-authored-by: zzzzwwjj <1183291235@qq.com> Co-authored-by: linfeng-yuan <1102311262@qq.com> Co-authored-by: wxsIcey <1790571317@qq.com> Co-authored-by: MengqingCao <cmq0113@163.com>
61 lines
2.2 KiB
Python
61 lines
2.2 KiB
Python
from vllm import ModelRegistry
|
|
|
|
import vllm_ascend.envs as envs_ascend
|
|
|
|
|
|
def register_model():
|
|
ModelRegistry.register_model(
|
|
"Qwen2VLForConditionalGeneration",
|
|
"vllm_ascend.models.qwen2_vl:AscendQwen2VLForConditionalGeneration")
|
|
|
|
ModelRegistry.register_model(
|
|
"Qwen3VLMoeForConditionalGeneration",
|
|
"vllm_ascend.models.qwen2_5_vl_without_padding:AscendQwen3VLMoeForConditionalGeneration"
|
|
)
|
|
|
|
ModelRegistry.register_model(
|
|
"Qwen3VLForConditionalGeneration",
|
|
"vllm_ascend.models.qwen2_5_vl_without_padding:AscendQwen3VLForConditionalGeneration"
|
|
)
|
|
|
|
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"
|
|
)
|
|
|
|
ModelRegistry.register_model(
|
|
"DeepseekV2ForCausalLM",
|
|
"vllm_ascend.models.deepseek_v2:CustomDeepseekV2ForCausalLM")
|
|
|
|
ModelRegistry.register_model(
|
|
"DeepseekV3ForCausalLM",
|
|
"vllm_ascend.models.deepseek_v2:CustomDeepseekV3ForCausalLM")
|
|
|
|
ModelRegistry.register_model(
|
|
"DeepseekV32ForCausalLM",
|
|
"vllm_ascend.models.deepseek_v2:CustomDeepseekV3ForCausalLM")
|
|
|
|
ModelRegistry.register_model(
|
|
"DeepSeekMTPModel",
|
|
"vllm_ascend.models.deepseek_mtp:CustomDeepSeekMTP")
|
|
|
|
ModelRegistry.register_model(
|
|
"Qwen3MoeForCausalLM",
|
|
"vllm_ascend.models.qwen3_moe:CustomQwen3MoeForCausalLM")
|
|
|
|
# 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:CustomQwen3NextForCausalLM")
|