ZT-AIA 6cb76ecd02 [Nightly] Avoid max_model_len being smaller than the decoder prompt to prevent single-node-accuray-tests from failing (#5174) ...

### What this PR does / why we need it?
[Nightly] Avoid max_model_len being smaller than the decoder prompt to
prevent single-node-accuray-tests from failing
### Does this PR introduce _any_ user-facing change?
No
### How was this patch tested?

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

---------

Signed-off-by: ZT-AIA <1028681969@qq.com>
Signed-off-by: ZT-AIA <63220130+ZT-AIA@users.noreply.github.com>

2025-12-18 22:25:45 +08:00

..

configs

[Nightly] Avoid max_model_len being smaller than the decoder prompt to prevent single-node-accuray-tests from failing (#5174)

2025-12-18 22:25:45 +08:00

conftest.py

[E2E] Optimize nightly testcase. (#4886)

2025-12-11 10:15:39 +08:00

report_template.md

[Fixbug] Fix accuarcy template (#3088)

2025-10-10 09:03:21 +08:00

test_lm_eval_correctness.py

[Test] Add accuracy nightly test for new models (#4262)

2025-12-01 22:28:46 +08:00