[CI] Add skipped testcases. (#5254)
### What this PR does / why we need it? Some E2E testcases are not in our CI workflow, this PR add them back. - vLLM version: release/v0.13.0 - vLLM main: https://github.com/vllm-project/vllm/commit/ad32e3e19ccf0526cb6744a5fed09a138a5fb2f9 Signed-off-by: menogrey <1299267905@qq.com>
This commit is contained in:
1 parent
7ff1db4b84
commit
bd4fb871c6
2 files changed
+8
No files matched your search
@@ -117,6 +117,7 @@ jobs:
|
||||
pytest -sv --durations=0 tests/e2e/singlecard/pooling/
|
||||
pytest -sv --durations=0 tests/e2e/singlecard/compile/test_norm_quant_fusion.py
|
||||
pytest -sv --durations=0 tests/e2e/singlecard/test_cross_layer_attn_model.py
|
||||
pytest -sv --durations=0 tests/e2e/singlecard/test_multistream_overlap_shared_expert.py
|
||||
|
||||
# ------------------------------------ v1 spec decode test ------------------------------------ #
|
||||
pytest -sv --durations=0 tests/e2e/singlecard/spec_decode_v1/test_v1_mtp_correctness.py
|
||||
@@ -219,6 +220,7 @@ jobs:
|
||||
pytest -sv --durations=0 tests/e2e/multicard/test_offline_inference_distributed.py::test_qwen3_dense_fc1_tp2
|
||||
pytest -sv --durations=0 tests/e2e/multicard/test_offline_inference_distributed.py::test_qwen3_dense_prefetch_mlp_weight_tp2
|
||||
pytest -sv --durations=0 tests/e2e/multicard/test_offline_inference_distributed.py::test_deepseek_w4a8_accuracy_tp2
|
||||
pytest -sv --durations=0 tests/e2e/multicard/test_offline_inference_distributed.py::test_deepseek_v2_lite_fc1_tp2
|
||||
|
||||
pytest -sv --durations=0 tests/e2e/multicard/test_prefix_caching.py
|
||||
pytest -sv --durations=0 tests/e2e/multicard/test_pipeline_parallel.py
|
||||
|
||||
@@ -48,9 +48,11 @@ def test_models_with_multistream_overlap_shared_expert(
|
||||
model,
|
||||
max_model_len=1024,
|
||||
enforce_eager=True,
|
||||
cudagraph_capture_sizes=[4, 8, 16, 32],
|
||||
additional_config={
|
||||
"multistream_overlap_shared_expert": True,
|
||||
},
|
||||
quantization="ascend",
|
||||
) as runner:
|
||||
vllm_moe_ms_eager_outputs = runner.model.generate(
|
||||
prompts, sampling_params)
|
||||
@@ -58,9 +60,11 @@ def test_models_with_multistream_overlap_shared_expert(
|
||||
with VllmRunner(
|
||||
model,
|
||||
max_model_len=1024,
|
||||
cudagraph_capture_sizes=[4, 8, 16, 32],
|
||||
additional_config={
|
||||
"multistream_overlap_shared_expert": True,
|
||||
},
|
||||
quantization="ascend",
|
||||
) as runner:
|
||||
vllm_moe_ms_aclgraph_outputs = runner.model.generate(
|
||||
prompts, sampling_params)
|
||||
@@ -69,6 +73,8 @@ def test_models_with_multistream_overlap_shared_expert(
|
||||
model,
|
||||
max_model_len=1024,
|
||||
enforce_eager=True,
|
||||
cudagraph_capture_sizes=[4, 8, 16, 32],
|
||||
quantization="ascend",
|
||||
) as runner:
|
||||
vllm_eager_outputs = runner.model.generate(prompts, sampling_params)
|
||||
|
||||
|
||||
Reference in new issue
Block a user