[Refact.]: Refactor some leftover implementations of 300I DUO in the main branch. (#6425)

### What this PR does / why we need it?
- Replace the RoPE operator implementation.
- Refactor some leftover implementations of 300I DUO in the main branch.

### Does this PR introduce _any_ user-facing change?
NA
### How was this patch tested?

- vLLM version: v0.14.1
- vLLM main:
dc917cceb8

---------

Signed-off-by: Tflowers-0129 <2906339855@qq.com>
This commit is contained in:
Shaoxu Cheng
2026-02-02 16:12:04 +08:00
committed by GitHub
parent eeedf7c503
commit 460ea88276
7 changed files with 94 additions and 23 deletions

View File

@@ -26,7 +26,8 @@ class NPUWorker310(NPUWorker):
def init_device(self):
self.device = self._init_device()
torch_npu.npu.set_compile_mode(jit_compile=False)
# TODO: There is accuracy issue when jit_compile is disabled currently.
torch_npu.npu.set_compile_mode(jit_compile=True)
init_workspace_manager(self.device, num_ubatches=1)