[Test] Add new e2e test use deepseek-v2-lite in ge graph mode (#3937)

### What this PR does / why we need it?
The current test cases lack end-to-end (e2e) testing for the
deepseek-v2-lite network in ge graph mode.
### Does this PR introduce _any_ user-facing change?
No
### How was this patch tested?

- vLLM version: v0.11.0
- vLLM main:
83f478bb19

---------

Signed-off-by: CodeNine-CJ <chenjian343@huawei.com>
This commit is contained in:
CodeCat
2025-11-03 20:10:01 +08:00
committed by GitHub
parent 8f222f21f1
commit 49d74785c4
2 changed files with 68 additions and 3 deletions

View File

@@ -74,8 +74,8 @@ jobs:
PYTORCH_NPU_ALLOC_CONF: max_split_size_mb:256
if: ${{ inputs.type == 'light' }}
run: |
pytest -sv tests/e2e/singlecard/test_aclgraph.py
pytest -sv tests/e2e/singlecard/test_quantization.py
# pytest -sv tests/e2e/singlecard/test_aclgraph.py
# pytest -sv tests/e2e/singlecard/test_quantization.py
pytest -sv tests/e2e/singlecard/test_vlm.py::test_multimodal_vl
- name: Run e2e test
@@ -171,6 +171,7 @@ jobs:
if: ${{ inputs.type == 'light' }}
run: |
pytest -sv tests/e2e/multicard/test_qwen3_moe.py::test_models_distributed_Qwen3_MOE_TP2_WITH_EP
pytest -sv tests/e2e/multicard/test_torchair_graph_mode.py::test_e2e_deepseekv2lite_with_torchair
- name: Run vllm-project/vllm-ascend test (full)
env:
@@ -178,6 +179,7 @@ jobs:
VLLM_USE_MODELSCOPE: True
if: ${{ inputs.type == 'full' }}
run: |
pytest -sv tests/e2e/multicard/test_torchair_graph_mode.py
pytest -sv tests/e2e/multicard/test_data_parallel.py
pytest -sv tests/e2e/multicard/test_expert_parallel.py
# pytest -sv tests/e2e/multicard/test_external_launcher.py
@@ -199,4 +201,4 @@ jobs:
pytest -sv tests/e2e/multicard/test_pipeline_parallel.py
pytest -sv tests/e2e/multicard/test_prefix_caching.py
pytest -sv tests/e2e/multicard/test_qwen3_moe.py
pytest -sv tests/e2e/multicard/test_torchair_graph_mode.py