Files
xc-llm-ascend/vllm_ascend/models/__init__.py
rjg-lyh 6b7117dbb7 [main] addrmsnorm + quant fusion optim in Dense Models (#2772)
### What this PR does / why we need it?
This PR fused addrmsnorm op and w8a8 quant op to get better perf.

### Does this PR introduce _any_ user-facing change?
No.

### How was this patch tested?
CI passed with new added/existing test.

- vLLM version: v0.10.2
- vLLM main:
0faf3cc3e8

Signed-off-by: rjg-lyh <1318825571@qq.com>
2025-09-16 22:31:38 +08:00

47 lines
1.7 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")
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_v3: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:Qwen3NextForCausalLM")