[Quantization] register AscendQuantRMSNorm for quantization (#2856)

### What this PR does / why we need it?

modelslim will generate self.bias for rms norm in quantization, since
RMSNorm in vllm has no this parameter, so its nesscesary
to create a AscendQuantRmsNorm.
### Does this PR introduce _any_ user-facing change?
No

### How was this patch tested?

tested by deepseek-v3.1-w8a8

<img width="2496" height="592" alt="image"
src="https://github.com/user-attachments/assets/004c6e76-3d7a-4a1f-b59f-a14304012663"
/>


- vLLM version: main
- vLLM main:
d6249d0699

Signed-off-by: 22dimensions <waitingwind@foxmail.com>
This commit is contained in:
22dimensions
2025-09-11 23:14:02 +08:00
committed by GitHub
parent eab3635850
commit f5a97e8fa5
4 changed files with 35 additions and 7 deletions

View File

@@ -83,7 +83,7 @@ class NPUWorker(WorkerBase):
from vllm_ascend import ops
ops.register_dummy_fusion_op()
_register_atb_extensions()
register_ascend_customop()
register_ascend_customop(vllm_config)
# init ascend config and soc version
init_ascend_config(vllm_config)
init_ascend_soc_version()