[Test] add test for prefix cache feature of deepseek (#3733)

### What this PR does / why we need it?
This PR adds a prefix cache case for nightly test for
DeepSeek-r1-0528-W8A8 on A3, we need test them daily.

### Does this PR introduce _any_ user-facing change?
No

### How was this patch tested?
By running the test

- vLLM version: v0.11.0rc3
- vLLM main:
17c540a993

---------

Signed-off-by: root <root@hostname-2pbfv.foreman.pxe>
Co-authored-by: root <root@hostname-2pbfv.foreman.pxe>
This commit is contained in:
HuaJiaHeng
2025-10-25 14:08:15 +08:00
committed by GitHub
parent 1f25d60870
commit 11f75883be
2 changed files with 127 additions and 0 deletions

View File

@@ -65,6 +65,9 @@ jobs:
- name: deepseek-r1-0528-w8a8
os: linux-aarch64-a3-16
tests: tests/e2e/nightly/models/test_deepseek_r1_0528_w8a8.py
- name: deepseek-r1-0528-w8a8-prefix-cache
os: linux-aarch64-a3-16
tests: tests/e2e/nightly/features/test_prefix_cache_deepseek_r1_0528_w8a8.py
uses: ./.github/workflows/_e2e_nightly_single_node.yaml
with:
vllm: v0.11.0