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

[E2E] Collect test run time. (#5018)

Browse Source 
### What this PR does / why we need it?
[E2E] Collect test run time.

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

Signed-off-by: menogrey <1299267905@qq.com>
This commit is contained in:
zhangyiming
2025-12-15 20:06:48 +08:00
committed by GitHub
parent 019c8e03c2
commit e90e8afc94
1 changed files with 46 additions and 46 deletions
Download Patch File Download Diff File Expand all files Collapse all files

92
.github/workflows/_e2e_test.yaml vendored
View File

@@ -75,10 +75,10 @@ jobs:
PYTORCH_NPU_ALLOC_CONF: max_split_size_mb:256
if: ${{ inputs.type == 'light' }}
run: |
# pytest -sv tests/e2e/singlecard/test_aclgraph_accuracy.py
# pytest -sv tests/e2e/singlecard/test_quantization.py
pytest -sv tests/e2e/singlecard/test_vlm.py::test_multimodal_vl
pytest -sv tests/e2e/singlecard/pooling/test_classification.py::test_classify_correctness
# 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_vlm.py::test_multimodal_vl
pytest -sv --durations=0 tests/e2e/singlecard/pooling/test_classification.py::test_classify_correctness
- name: Run e2e test
env:
@@ -90,25 +90,25 @@ jobs:
# We found that if running aclgraph tests in batch, it will cause AclmdlRICaptureBegin error. So we run
# the test separately.
pytest -sv tests/e2e/singlecard/test_completion_with_prompt_embeds.py
pytest -sv tests/e2e/singlecard/test_aclgraph_accuracy.py
pytest -sv tests/e2e/singlecard/test_aclgraph_mem.py
pytest -sv tests/e2e/singlecard/test_async_scheduling.py
pytest -sv tests/e2e/singlecard/test_camem.py
pytest -sv tests/e2e/singlecard/test_guided_decoding.py
pytest -sv --durations=0 tests/e2e/singlecard/test_completion_with_prompt_embeds.py
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_camem.py
pytest -sv --durations=0 tests/e2e/singlecard/test_guided_decoding.py
# torch 2.8 doesn't work with lora, fix me
#pytest -sv tests/e2e/singlecard/test_ilama_lora.py
pytest -sv tests/e2e/singlecard/test_profile_execute_duration.py
pytest -sv tests/e2e/singlecard/test_quantization.py
pytest -sv tests/e2e/singlecard/test_sampler.py
pytest -sv tests/e2e/singlecard/test_vlm.py
pytest -sv tests/e2e/singlecard/test_xlite.py
pytest -sv tests/e2e/singlecard/pooling/
pytest -sv tests/e2e/singlecard/compile/test_norm_quant_fusion.py
#pytest -sv --durations=0 tests/e2e/singlecard/test_ilama_lora.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/pooling/
pytest -sv --durations=0 tests/e2e/singlecard/compile/test_norm_quant_fusion.py
# ------------------------------------ v1 spec decode test ------------------------------------ #
pytest -sv tests/e2e/singlecard/spec_decode_v1/test_v1_mtp_correctness.py
pytest -sv tests/e2e/singlecard/spec_decode_v1/test_v1_spec_decode.py
pytest -sv --durations=0 tests/e2e/singlecard/spec_decode_v1/test_v1_mtp_correctness.py
pytest -sv --durations=0 tests/e2e/singlecard/spec_decode_v1/test_v1_spec_decode.py
e2e-2-cards:
name: multicard-2
@@ -170,7 +170,7 @@ jobs:
VLLM_USE_MODELSCOPE: True
if: ${{ inputs.type == 'light' }}
run: |
pytest -sv tests/e2e/multicard/test_qwen3_moe.py::test_qwen3_moe_distributed_mp_tp2_ep
pytest -sv --durations=0 tests/e2e/multicard/test_qwen3_moe.py::test_qwen3_moe_distributed_mp_tp2_ep
- name: Run vllm-project/vllm-ascend test (full)
env:
@@ -178,30 +178,30 @@ jobs:
VLLM_USE_MODELSCOPE: True
if: ${{ inputs.type == 'full' }}
run: |
pytest -sv tests/e2e/multicard/test_quantization.py
pytest -sv tests/e2e/multicard/test_aclgraph_capture_replay.py
pytest -sv tests/e2e/multicard/test_full_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
pytest -sv tests/e2e/multicard/test_single_request_aclgraph.py
pytest -sv tests/e2e/multicard/test_fused_moe_allgather_ep.py
pytest -sv --durations=0 tests/e2e/multicard/test_quantization.py
pytest -sv --durations=0 tests/e2e/multicard/test_aclgraph_capture_replay.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/test_fused_moe_allgather_ep.py
# torch 2.8 doesn't work with lora, fix me
#pytest -sv tests/e2e/multicard/test_ilama_lora_tp2.py
#pytest -sv --durations=0 tests/e2e/multicard/test_ilama_lora_tp2.py
# To avoid oom, we need to run the test in a single process.
pytest -sv tests/e2e/multicard/test_offline_inference_distributed.py::test_models_distributed_DeepSeek_multistream_moe
pytest -sv tests/e2e/multicard/test_offline_inference_distributed.py::test_models_distributed_Qwen3_W4A8DYNAMIC
pytest -sv tests/e2e/multicard/test_offline_inference_distributed.py::test_models_distributed_DeepSeek_W4A8DYNAMIC
pytest -sv tests/e2e/multicard/test_offline_inference_distributed.py::test_sp_for_qwen3_moe
pytest -sv tests/e2e/multicard/test_offline_inference_distributed.py::test_fc2_for_qwen3_moe
pytest -sv tests/e2e/multicard/test_offline_inference_distributed.py::test_models_distributed_Qwen_Dense_with_flashcomm_v1
pytest -sv tests/e2e/multicard/test_offline_inference_distributed.py::test_models_distributed_Qwen_Dense_with_prefetch_mlp_weight
pytest -sv --durations=0 tests/e2e/multicard/test_offline_inference_distributed.py::test_models_distributed_DeepSeek_multistream_moe
pytest -sv --durations=0 tests/e2e/multicard/test_offline_inference_distributed.py::test_models_distributed_Qwen3_W4A8DYNAMIC
pytest -sv --durations=0 tests/e2e/multicard/test_offline_inference_distributed.py::test_models_distributed_DeepSeek_W4A8DYNAMIC
pytest -sv --durations=0 tests/e2e/multicard/test_offline_inference_distributed.py::test_sp_for_qwen3_moe
pytest -sv --durations=0 tests/e2e/multicard/test_offline_inference_distributed.py::test_fc2_for_qwen3_moe
pytest -sv --durations=0 tests/e2e/multicard/test_offline_inference_distributed.py::test_models_distributed_Qwen_Dense_with_flashcomm_v1
pytest -sv --durations=0 tests/e2e/multicard/test_offline_inference_distributed.py::test_models_distributed_Qwen_Dense_with_prefetch_mlp_weight
pytest -sv tests/e2e/multicard/test_prefix_caching.py
pytest -sv tests/e2e/multicard/test_pipeline_parallel.py
pytest -sv tests/e2e/multicard/test_qwen3_moe.py
pytest -sv tests/e2e/multicard/test_offline_weight_load.py
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
e2e-4-cards:
name: multicard-4
@@ -264,10 +264,10 @@ jobs:
VLLM_WORKER_MULTIPROC_METHOD: spawn
VLLM_USE_MODELSCOPE: True
run: |
pytest -sv tests/e2e/multicard/test_offline_inference_distributed.py::test_models_distributed_DeepSeek_multistream_moe
pytest -sv tests/e2e/multicard/test_offline_inference_distributed.py::test_models_distributed_DeepSeek_W4A8DYNAMIC
pytest -sv tests/e2e/multicard/test_offline_inference_distributed.py::test_models_distributed_Kimi_K2_Thinking_W4A16
pytest -sv tests/e2e/multicard/test_data_parallel_tp2.py
pytest -sv --durations=0 tests/e2e/multicard/test_offline_inference_distributed.py::test_models_distributed_DeepSeek_multistream_moe
pytest -sv --durations=0 tests/e2e/multicard/test_offline_inference_distributed.py::test_models_distributed_DeepSeek_W4A8DYNAMIC
pytest -sv --durations=0 tests/e2e/multicard/test_offline_inference_distributed.py::test_models_distributed_Kimi_K2_Thinking_W4A16
pytest -sv --durations=0 tests/e2e/multicard/test_data_parallel_tp2.py
- name: Install Ascend toolkit & triton_ascend (for Qwen3-Next-80B-A3B-Instruct)
shell: bash -l {0}
@@ -283,4 +283,4 @@ jobs:
VLLM_USE_MODELSCOPE: True
run: |
. /usr/local/Ascend/ascend-toolkit/8.3.RC2/bisheng_toolkit/set_env.sh
pytest -sv tests/e2e/multicard/test_qwen3_next.py
pytest -sv --durations=0 tests/e2e/multicard/test_qwen3_next.py