[Refactor] Remove dead code in kv connector and model runner (#38383)

Signed-off-by: yewentao256 <zhyanwentao@126.com>
This commit is contained in:
Wentao Ye
2026-03-31 17:05:23 -04:00
committed by GitHub
parent 517b769b58
commit 856589ed9a
7 changed files with 16 additions and 54 deletions
-4
View File
@@ -102,10 +102,6 @@ class CPUModelRunner(GPUModelRunner):
# so stale KV cache data never affects computation.
pass
def get_dp_padding(self, num_tokens: int) -> tuple[int, torch.Tensor | None]:
# Note: For CPU backend, dp padding is not required for now.
return 0, None
@contextmanager
def _torch_cuda_wrapper():