[BugFix] Fix npu-cpu offloading interface change bug. (#5290)

### What this PR does / why we need it?
Last month the interface of `OffloadingSpec` has
changed(https://github.com/vllm-project/vllm/pull/27743). This PR fixes
this bug and adds e2e test for cpu offloading.

### Does this PR introduce _any_ user-facing change?
None

### How was this patch tested?
CI passed with new added test.


- vLLM version: release/v0.13.0
- vLLM main:
ad32e3e19c

---------

Signed-off-by: whx-sjtu <2952154980@qq.com>
This commit is contained in:
whx
2025-12-27 10:21:20 +08:00
committed by GitHub
parent 2ef4d1979e
commit 3f33ad23fe
3 changed files with 184 additions and 12 deletions

View File

@@ -119,6 +119,7 @@ jobs:
pytest -sv --durations=0 tests/e2e/singlecard/pooling/
pytest -sv --durations=0 tests/e2e/singlecard/compile/test_norm_quant_fusion.py
pytest -sv --durations=0 tests/e2e/singlecard/test_multistream_overlap_shared_expert.py
pytest -sv --durations=0 tests/e2e/singlecard/test_cpu_offloading.py
# ------------------------------------ v1 spec decode test ------------------------------------ #
pytest -sv --durations=0 tests/e2e/singlecard/spec_decode_v1/test_v1_mtp_correctness.py