weichen cec1fab509 Revert "[MoE] [Refactor] Remove manual memory cleanup (#3365)" (#3483) ...

This reverts commit 4f937f561d.

### What this PR does / why we need it?
This reverts commit 4f937f561d.
### Does this PR introduce _any_ user-facing change?
No
### How was this patch tested?
e2e & ut

- vLLM version: v0.11.0rc3
- vLLM main: https://github.com/vllm-project/vllm/commit/v0.11.0

Signed-off-by: Pr0Wh1teGivee <calvin_zhu0210@outlook.com>

2025-10-15 22:25:46 +08:00

..

__init__.py

[CI] Add unit test framework (#1201)

2025-06-16 18:32:28 +08:00

test_bgmv_expand.py

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

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

test_bgmv_shrink.py

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

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

test_fused_moe.py

Revert "[MoE] [Refactor] Remove manual memory cleanup (#3365)" (#3483)

2025-10-15 22:25:46 +08:00

test_gating_top_k_softmax.py

use npu_moe_gating_top_k_softmax (#1355)

2025-07-11 08:55:06 +08:00

test_mla_preprocess.py

add mla_preprocess kernel (#3226)

2025-10-12 07:39:45 +08:00

test_rotary_embedding.py

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

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

test_vocabparallelembedding.py

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

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