EngineX/xc-llm-ascend
3
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

[CI] cleanup single/multi-card test (#5623)

Browse Source 
1. speed up e2e light test.
2. create `2-cards` and `4-cards` folder in multicard
3. move ops to nightly
4. run test in Alphabetical Order

- vLLM version: v0.13.0
- vLLM main:
8be6432bda

Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>
This commit is contained in:
wangxiyuan
2026-01-07 14:13:34 +08:00
committed by GitHub
parent 1afbc01ed4
commit 6f7a81cd9f
30 changed files with 114 additions and 117 deletions
Download Patch File Download Diff File Expand all files Collapse all files

105
.github/workflows/_e2e_test.yaml vendored
View File

@@ -83,12 +83,8 @@ jobs:
VLLM_WORKER_MULTIPROC_METHOD: spawn
if: ${{ inputs.type == 'light' }}
run: |
# pytest -sv --durations=0 tests/e2e/singlecard/test_aclgraph_accuracy.py
# pytest -sv --durations=0 tests/e2e/singlecard/test_quantization.py
pytest -sv --durations=0 tests/e2e/singlecard/test_aclgraph_mem.py
pytest -sv --durations=0 tests/e2e/singlecard/test_camem.py
pytest -sv --durations=0 tests/e2e/singlecard/test_vlm.py::test_multimodal_vl
pytest -sv --durations=0 tests/e2e/singlecard/pooling/test_classification.py::test_qwen_pooling_classify_correctness
pytest -sv --durations=0 tests/e2e/singlecard/test_aclgraph_accuracy.py::test_models_output
pytest -sv --durations=0 tests/e2e/singlecard/test_quantization.py::test_qwen3_w8a8_quant
- name: Run e2e test
env:
@@ -98,33 +94,41 @@ jobs:
run: |
# We found that if running aclgraph tests in batch, it will cause AclmdlRICaptureBegin error. So we run
# the test separately.
pytest -sv --durations=0 tests/e2e/nightly/single_node/ops/singlecard_ops/triton/
pytest -sv --durations=0 tests/e2e/singlecard/test_completion_with_prompt_embeds.py
# basic
pytest -sv --durations=0 tests/e2e/singlecard/test_aclgraph_accuracy.py
pytest -sv --durations=0 tests/e2e/singlecard/test_aclgraph_mem.py
pytest -sv --durations=0 tests/e2e/singlecard/test_async_scheduling.py
pytest -sv --durations=0 tests/e2e/singlecard/test_batch_invariant.py
pytest -sv --durations=0 tests/e2e/singlecard/test_camem.py
pytest -sv --durations=0 tests/e2e/singlecard/test_completion_with_prompt_embeds.py
pytest -sv --durations=0 tests/e2e/singlecard/test_cpu_offloading.py
# xgrammar has parameter mismatching bug, please follows: https://github.com/vllm-project/vllm-ascend/issues/5524
# pytest -sv --durations=0 tests/e2e/singlecard/test_guided_decoding.py
# torch 2.8 doesn't work with lora, fix me
#pytest -sv --durations=0 tests/e2e/singlecard/test_ilama_lora.py
pytest -sv --durations=0 tests/e2e/singlecard/test_models.py
pytest -sv --durations=0 tests/e2e/singlecard/test_multistream_overlap_shared_expert.py
pytest -sv --durations=0 tests/e2e/singlecard/test_profile_execute_duration.py
pytest -sv --durations=0 tests/e2e/singlecard/test_quantization.py
pytest -sv --durations=0 tests/e2e/singlecard/test_sampler.py
pytest -sv --durations=0 tests/e2e/singlecard/test_vlm.py
pytest -sv --durations=0 tests/e2e/singlecard/test_xlite.py
pytest -sv --durations=0 tests/e2e/singlecard/test_models.py
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_multistream_overlap_shared_expert.py
pytest -sv --durations=0 tests/e2e/singlecard/test_cpu_offloading.py
# ------------------------------------ v1 spec decode test ------------------------------------ #
# compile
pytest -sv --durations=0 tests/e2e/singlecard/compile/test_norm_quant_fusion.py
# model_runner_v2
pytest -sv --durations=0 tests/e2e/singlecard/model_runner_v2/test_basic.py
# pooling
pytest -sv --durations=0 tests/e2e/singlecard/pooling/test_classification.py
pytest -sv --durations=0 tests/e2e/singlecard/pooling/test_embedding.py
pytest -sv --durations=0 tests/e2e/singlecard/pooling/test_scoring.py
# spec_decode
pytest -sv --durations=0 tests/e2e/singlecard/spec_decode/test_mtp_eagle_correctness.py
pytest -sv --durations=0 tests/e2e/singlecard/spec_decode/test_v1_spec_decode.py
pytest -sv --durations=0 tests/e2e/singlecard/model_runner_v2/test_basic.py
pytest -sv --durations=0 tests/e2e/singlecard/test_batch_invariant.py
e2e-2-cards:
name: multicard-2
runs-on: linux-aarch64-a3-2
@@ -184,7 +188,7 @@ jobs:
env:
VLLM_WORKER_MULTIPROC_METHOD: spawn
run: |
pytest -sv --durations=0 tests/e2e/multicard/test_aclgraph_capture_replay.py
pytest -sv --durations=0 tests/e2e/multicard/2-cards/test_aclgraph_capture_replay.py
- name: Install Ascend toolkit & triton_ascend
shell: bash -l {0}
@@ -200,36 +204,39 @@ jobs:
VLLM_WORKER_MULTIPROC_METHOD: spawn
if: ${{ inputs.type == 'light' }}
run: |
pytest -sv --durations=0 tests/e2e/multicard/test_qwen3_moe.py::test_qwen3_moe_distributed_mp_tp2_ep
pytest -sv --durations=0 tests/e2e/multicard/2-cards/test_qwen3_moe.py::test_qwen3_moe_distributed_mp_tp2_ep
- name: Run vllm-project/vllm-ascend test (full)
env:
VLLM_WORKER_MULTIPROC_METHOD: spawn
if: ${{ inputs.type == 'full' }}
run: |
pytest -sv --durations=0 tests/e2e/multicard/test_quantization.py
pytest -sv --durations=0 tests/e2e/multicard/test_full_graph_mode.py
pytest -sv --durations=0 tests/e2e/multicard/test_data_parallel.py
pytest -sv --durations=0 tests/e2e/multicard/test_expert_parallel.py
pytest -sv --durations=0 tests/e2e/multicard/test_external_launcher.py
pytest -sv --durations=0 tests/e2e/multicard/test_single_request_aclgraph.py
pytest -sv --durations=0 tests/e2e/multicard/2-cards/test_data_parallel.py
pytest -sv --durations=0 tests/e2e/multicard/2-cards/test_expert_parallel.py
pytest -sv --durations=0 tests/e2e/multicard/2-cards/test_external_launcher.py
pytest -sv --durations=0 tests/e2e/multicard/2-cards/test_full_graph_mode.py
# torch 2.8 doesn't work with lora, fix me
#pytest -sv --durations=0 tests/e2e/multicard/test_ilama_lora_tp2.py
#pytest -sv --durations=0 tests/e2e/multicard/2-cards/test_ilama_lora_tp2.py
# To avoid oom, we need to run the test in a single process.
pytest -sv --durations=0 tests/e2e/multicard/test_offline_inference_distributed.py::test_deepseek_multistream_moe_tp2
pytest -sv --durations=0 tests/e2e/multicard/test_offline_inference_distributed.py::test_qwen3_w4a8_dynamic_tp2
pytest -sv --durations=0 tests/e2e/multicard/test_offline_inference_distributed.py::test_qwen3_moe_sp_tp2
pytest -sv --durations=0 tests/e2e/multicard/test_offline_inference_distributed.py::test_qwen3_moe_fc2_tp2
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/2-cards/test_offline_inference_distributed.py::test_deepseek_multistream_moe_tp2
pytest -sv --durations=0 tests/e2e/multicard/2-cards/test_offline_inference_distributed.py::test_qwen3_w4a8_dynamic_tp2
pytest -sv --durations=0 tests/e2e/multicard/2-cards/test_offline_inference_distributed.py::test_qwen3_moe_sp_tp2
pytest -sv --durations=0 tests/e2e/multicard/2-cards/test_offline_inference_distributed.py::test_deepseek_w4a8_accuracy_tp2
pytest -sv --durations=0 tests/e2e/multicard/2-cards/test_offline_inference_distributed.py::test_qwen3_moe_fc2_tp2
pytest -sv --durations=0 tests/e2e/multicard/2-cards/test_offline_inference_distributed.py::test_deepseek_v2_lite_fc1_tp2
pytest -sv --durations=0 tests/e2e/multicard/2-cards/test_offline_inference_distributed.py::test_qwen3_dense_fc1_tp2
pytest -sv --durations=0 tests/e2e/multicard/2-cards/test_offline_inference_distributed.py::test_qwen3_dense_prefetch_mlp_weight_tp2
pytest -sv --durations=0 tests/e2e/multicard/test_prefix_caching.py
pytest -sv --durations=0 tests/e2e/multicard/test_pipeline_parallel.py
pytest -sv --durations=0 tests/e2e/multicard/test_qwen3_moe.py
pytest -sv --durations=0 tests/e2e/multicard/test_offline_weight_load.py
pytest -sv --durations=0 tests/e2e/multicard/2-cards/test_offline_weight_load.py
pytest -sv --durations=0 tests/e2e/multicard/2-cards/test_pipeline_parallel.py
pytest -sv --durations=0 tests/e2e/multicard/2-cards/test_prefix_caching.py
pytest -sv --durations=0 tests/e2e/multicard/2-cards/test_quantization.py
pytest -sv --durations=0 tests/e2e/multicard/2-cards/test_qwen3_moe.py
# This test is broken, fix me
#pytest -sv --durations=0 tests/e2e/multicard/2-cards/test_shared_expert_dp.py
pytest -sv --durations=0 tests/e2e/multicard/2-cards/test_single_request_aclgraph.py
e2e-4-cards:
name: multicard-4
@@ -300,11 +307,15 @@ jobs:
env:
VLLM_WORKER_MULTIPROC_METHOD: spawn
run: |
pytest -sv --durations=0 tests/e2e/multicard/spec_decode/test_mtp_qwen3_next.py
pytest -sv --durations=0 tests/e2e/multicard/test_offline_inference_distributed.py::test_deepseek_multistream_moe_tp2
pytest -sv --durations=0 tests/e2e/multicard/test_offline_inference_distributed.py::test_kimi_k2_thinking_w4a16_tp4
pytest -sv --durations=0 tests/e2e/multicard/test_data_parallel_tp2.py
pytest -sv --durations=0 tests/e2e/multicard/long_sequence/test_basic.py
pytest -sv --durations=0 tests/e2e/multicard/long_sequence/test_accuracy.py
pytest -sv --durations=0 tests/e2e/multicard/long_sequence/test_mtp.py
pytest -sv --durations=0 tests/e2e/multicard/test_qwen3_next.py
pytest -sv --durations=0 tests/e2e/multicard/4-cards/test_data_parallel_tp2.py
pytest -sv --durations=0 tests/e2e/multicard/4-cards/test_kimi_k2.py
pytest -sv --durations=0 tests/e2e/multicard/4-cards/test_qwen3_next.py
# long_sequence
pytest -sv --durations=0 tests/e2e/multicard/4-cards/long_sequence/test_accuracy.py
pytest -sv --durations=0 tests/e2e/multicard/4-cards/long_sequence/test_basic.py
pytest -sv --durations=0 tests/e2e/multicard/4-cards/long_sequence/test_chunked_prefill.py
pytest -sv --durations=0 tests/e2e/multicard/4-cards/long_sequence/test_mtp.py
# spec_decode
pytest -sv --durations=0 tests/e2e/multicard/4-cards/spec_decode/test_mtp_qwen3_next.py