hukongyi ea8f544ce7 [BugFix]Fix precision issue for LoRA feature (#4141) ...

vLLM version: v0.11.0
vLLM main: vllm-project/vllm

### What this PR does / why we need it?
   Fix the precision issue of the LoRA feature in vllm-ascend.

### Does this PR introduce _any_ user-facing change?

### How was this patch tested?
```bash
pytest tests/lora/test_llama_tp.py::test_llama_lora -s
```
<img width="1319" height="879" alt="lora_test"
src="https://github.com/user-attachments/assets/2a0b2325-5b05-4bbc-ac03-a7c9f0ad9d4c"
/>


- vLLM version: v0.12.0
- vLLM main:
ad32e3e19c

---------

Signed-off-by: hukongyi <hukongyi@cmbchina.com>

2025-12-19 14:22:06 +08:00

..

__init__.py

[Bugfix] fix import error (#600)

2025-04-22 08:57:25 +08:00

lora_ops.py

Fix the bugs about operator registration by PyTorch Dispatcher (#2786)

2025-09-13 11:58:52 +08:00

punica_npu.py

[BugFix]Fix precision issue for LoRA feature (#4141)

2025-12-19 14:22:06 +08:00

utils.py

[Bugfix][LoRA] Fix LoRA bug after supporting Qwen3-Next (#3044)

2025-09-26 11:12:45 +08:00