Files
xc-llm-ascend/.github/workflows
fluctlux 9fbcfa36af [CI] Fix ngram & suffix test oom (#4755)
### What this PR does / why we need it?
Avoid oom during CI by using `with VllmRunner` instead of `LLM()`, and
enable `test_ngram_correctness`

### How was this patch tested?
CI passed.

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

---------

Signed-off-by: fluctlux <38945811+fluctlux@users.noreply.github.com>
Co-authored-by: wangxiyuan <wangxiyuan1007@gmail.com>
2025-12-08 09:26:29 +08:00
..
2025-02-05 10:53:12 +08:00