Files
xc-llm-ascend/vllm_ascend/patch/worker
Yaphets24andmayumeng 8977be1df3 [Bugfix]Fix deepseek 3.2 C8 precision by rotary tensor (#7537)
### What this PR does / why we need it?
During the attention quantization process of DeepSeek V3.2, it is
necessary to retrieve the Hadamard matrix from the weights to facilitate
the computation.

### Does this PR introduce _any_ user-facing change?
No. But there will be two new tensor in quant weight.

### How was this patch tested?

- vLLM version: v0.18.0
- vLLM main:
https://github.com/vllm-project/vllm/commit/8b6325758cce5f9c36d38f2462edbd368b97a07c

---------

Signed-off-by: mayumeng <m30059191@china.huawei.com>
Co-authored-by: mayumeng <m30059191@china.huawei.com>
2026-03-25 09:18:00 +08:00
..