vllm-ascend support Ascend950 with Qwen dense model. (#4228)
### What this PR does / why we need it?
vllm-ascend support Ascend950 with Qwen dense model
### Does this PR introduce _any_ user-facing change?
### How was this patch tested?
- vLLM version: v0.12.0
- vLLM main:
ad32e3e19c
---------
Signed-off-by: wangyao <iwangyao@outlook.com>
Co-authored-by: weijinqian0 <1184188277@qq.com>
This commit is contained in:
@@ -410,7 +410,8 @@ class AscendMRotaryEmbedding(MRotaryEmbedding):
|
||||
query: torch.Tensor,
|
||||
key: torch.Tensor,
|
||||
):
|
||||
if self.mrope_section != [16, 24, 24]:
|
||||
if self.mrope_section != [16, 24, 24] or \
|
||||
get_ascend_device_type() == AscendDeviceType._910_95:
|
||||
return super().forward_oot(positions, query, key)
|
||||
|
||||
import torch_npu
|
||||
|
||||
Reference in New Issue
Block a user