realliujiaxu 3581946256 [Bugfix] fix eagle proposer (#4971) ...

### What this PR does / why we need it?
After https://github.com/vllm-project/vllm-ascend/pull/4764, a lot of
tensor created by `make_buffer` should be renamed, like `input_ids` ->
`input_ids.gpu`.

- vLLM version: v0.12.0
- vLLM main:
ad32e3e19c

Signed-off-by: realliujiaxu <realliujiaxu@163.com>

2025-12-12 22:39:49 +08:00

..

__init__.py

Drop torchair (#4814)

2025-12-10 09:20:40 +08:00

eagle_proposer.py

[Bugfix] fix eagle proposer (#4971)

2025-12-12 22:39:49 +08:00

interface.py

upgrade vLLM to main (#4608)

2025-12-02 22:10:52 +08:00

mtp_proposer.py

[Feature] model_runner refactor (#4764)

2025-12-12 17:27:09 +08:00

ngram_proposer.py

upgrade vLLM to main (#4608)

2025-12-02 22:10:52 +08:00

suffix_proposer.py

[Feature] Integrate Suffix Spec Decoding (#4045)

2025-12-01 18:41:42 +08:00