9320365dab
### What this PR does / why we need it?
Add an e2e test for QuaRot model with eagle3 that runs both the QuaRot
model and the float model, and then compares their acceptance rates. The
QuaRot model adapting eagle3 PR(#6914, #7038)
- vLLM version: v0.16.0
- vLLM main:
4034c3d32e
Signed-off-by: zhaomingyu <zhaomingyu13@h-partners.com>
167 lines
7.1 KiB
YAML
167 lines
7.1 KiB
YAML
e2e-singlecard:
|
|
- name: tests/e2e/singlecard/compile/test_graphex_norm_quant_fusion.py
|
|
estimated_time: 80
|
|
- name: tests/e2e/singlecard/compile/test_graphex_qknorm_rope_fusion.py
|
|
estimated_time: 80
|
|
- name: tests/e2e/singlecard/test_auto_fit_max_mode_len.py
|
|
estimated_time: 25
|
|
- name: tests/e2e/singlecard/test_aclgraph_accuracy.py
|
|
estimated_time: 480
|
|
- name: tests/e2e/singlecard/test_aclgraph_batch_invariant.py
|
|
estimated_time: 410
|
|
- name: tests/e2e/singlecard/test_aclgraph_mem.py
|
|
estimated_time: 130
|
|
- name: tests/e2e/singlecard/test_async_scheduling.py
|
|
estimated_time: 150
|
|
- name: tests/e2e/singlecard/test_batch_invariant.py
|
|
estimated_time: 320
|
|
- name: tests/e2e/singlecard/test_camem.py
|
|
estimated_time: 77
|
|
- name: tests/e2e/singlecard/test_completion_with_prompt_embeds.py
|
|
estimated_time: 76
|
|
- name: tests/e2e/singlecard/test_cpu_offloading.py
|
|
estimated_time: 132
|
|
- name: tests/e2e/singlecard/test_guided_decoding.py
|
|
estimated_time: 354
|
|
- name: tests/e2e/singlecard/test_ilama_lora.py
|
|
estimated_time: 95
|
|
- name: tests/e2e/singlecard/test_llama32_lora.py
|
|
estimated_time: 162
|
|
- name: tests/e2e/singlecard/test_qwen3_multi_loras.py
|
|
estimated_time: 65
|
|
- name: tests/e2e/singlecard/test_models.py
|
|
estimated_time: 300
|
|
- name: tests/e2e/singlecard/test_multistream_overlap_shared_expert.py
|
|
estimated_time: 200
|
|
- name: tests/e2e/singlecard/test_quantization.py
|
|
estimated_time: 200
|
|
- name: tests/e2e/singlecard/test_sampler.py
|
|
estimated_time: 200
|
|
- name: tests/e2e/singlecard/test_vlm.py
|
|
estimated_time: 354
|
|
- name: tests/e2e/singlecard/test_xlite.py
|
|
estimated_time: 45
|
|
- name: tests/e2e/singlecard/compile/test_norm_quant_fusion.py
|
|
estimated_time: 70
|
|
- name: tests/e2e/singlecard/pooling/test_classification.py
|
|
estimated_time: 120
|
|
- name: tests/e2e/singlecard/pooling/test_embedding.py
|
|
estimated_time: 270
|
|
- name: tests/e2e/singlecard/pooling/test_scoring.py
|
|
estimated_time: 500
|
|
- name: tests/e2e/singlecard/pooling/test_qwen3_reranker_lora.py
|
|
estimated_time: 235
|
|
- name: tests/e2e/singlecard/spec_decode/test_mtp_eagle_correctness.py
|
|
estimated_time: 1500
|
|
- name: tests/e2e/singlecard/spec_decode/test_v1_spec_decode.py
|
|
estimated_time: 600
|
|
- name: tests/e2e/singlecard/model_runner_v2/test_basic.py
|
|
estimated_time: 80
|
|
is_skipped: true
|
|
|
|
e2e-singlecard-light:
|
|
- name: tests/e2e/singlecard/test_aclgraph_accuracy.py::test_piecewise_res_consistency
|
|
estimated_time: 220
|
|
- name: tests/e2e/singlecard/test_quantization.py::test_qwen3_w8a8_quant
|
|
estimated_time: 90
|
|
|
|
e2e-2card-light:
|
|
- name: tests/e2e/multicard/2-cards/test_qwen3_moe.py::test_qwen3_moe_distributed_mp_tp2_ep
|
|
estimated_time: 220
|
|
- name: tests/e2e/multicard/2-cards/test_offline_inference_distributed.py::test_deepseek3_2_w8a8_pruning_mtp_tp2_ep
|
|
estimated_time: 90
|
|
- name: tests/e2e/multicard/2-cards/test_offline_inference_distributed.py::test_gpt_oss_distributed_tp2
|
|
estimated_time: 180
|
|
|
|
e2e-multicard-2-cards:
|
|
# TODO: recover skipped tests
|
|
- name: tests/e2e/multicard/2-cards/test_aclgraph_capture_replay.py
|
|
estimated_time: 0
|
|
is_skipped: true
|
|
- name: tests/e2e/multicard/2-cards/spec_decode/test_spec_decode.py
|
|
estimated_time: 0
|
|
is_skipped: true
|
|
- name: tests/e2e/multicard/2-cards/test_offline_weight_load.py
|
|
estimated_time: 0
|
|
is_skipped: true
|
|
- name: tests/e2e/multicard/2-cards/test_shared_expert_dp.py
|
|
estimated_time: 0
|
|
is_skipped: true
|
|
- name: tests/e2e/multicard/2-cards/test_qwen3_performance.py
|
|
estimated_time: 180
|
|
- name: tests/e2e/multicard/2-cards/test_data_parallel.py
|
|
estimated_time: 380
|
|
- name: tests/e2e/multicard/2-cards/test_expert_parallel.py
|
|
estimated_time: 170
|
|
- name: tests/e2e/multicard/2-cards/test_external_launcher.py
|
|
estimated_time: 300
|
|
- name: tests/e2e/multicard/2-cards/test_full_graph_mode.py
|
|
estimated_time: 400
|
|
- name: tests/e2e/multicard/2-cards/test_ilama_lora_tp2.py
|
|
estimated_time: 60
|
|
- name: tests/e2e/multicard/2-cards/test_llama32_lora_tp2.py
|
|
estimated_time: 223
|
|
- name: tests/e2e/multicard/2-cards/spec_decode/test_quarot_eagle.py
|
|
estimated_time: 600
|
|
# Run the test in a separate step to avoid oom
|
|
- name: tests/e2e/multicard/2-cards/test_offline_inference_distributed.py::test_deepseek_multistream_moe_tp2
|
|
estimated_time: 100
|
|
- name: tests/e2e/multicard/2-cards/test_offline_inference_distributed.py::test_qwen3_w4a8_dynamic_tp2
|
|
estimated_time: 80
|
|
- name: tests/e2e/multicard/2-cards/test_offline_inference_distributed.py::test_qwen3_moe_sp_tp2
|
|
estimated_time: 132
|
|
- name: tests/e2e/multicard/2-cards/test_offline_inference_distributed.py::test_deepseek_w4a8_accuracy_tp2
|
|
estimated_time: 132
|
|
- name: tests/e2e/multicard/2-cards/test_offline_inference_distributed.py::test_qwen3_moe_fc2_tp2
|
|
estimated_time: 140
|
|
- name: tests/e2e/multicard/2-cards/test_offline_inference_distributed.py::test_deepseek_v2_lite_fc1_tp2
|
|
estimated_time: 82
|
|
- name: tests/e2e/multicard/2-cards/test_offline_inference_distributed.py::test_qwen3_dense_fc1_tp2
|
|
estimated_time: 73
|
|
- name: tests/e2e/multicard/2-cards/test_offline_inference_distributed.py::test_qwen3_dense_prefetch_mlp_weight_tp2
|
|
estimated_time: 71
|
|
- name: tests/e2e/multicard/2-cards/test_offline_inference_distributed.py::test_deepseek3_2_w8a8_pruning_mtp_tp2_ep
|
|
estimated_time: 111
|
|
- name: tests/e2e/multicard/2-cards/test_offline_inference_distributed.py::test_qwen3_w4a4_distributed_tp2
|
|
estimated_time: 180
|
|
- name: tests/e2e/multicard/2-cards/test_pipeline_parallel.py
|
|
estimated_time: 270
|
|
- name: tests/e2e/multicard/2-cards/test_prefix_caching.py
|
|
estimated_time: 430
|
|
- name: tests/e2e/multicard/2-cards/test_quantization.py
|
|
estimated_time: 70
|
|
- name: tests/e2e/multicard/2-cards/test_qwen3_moe.py
|
|
estimated_time: 1050
|
|
- name: tests/e2e/multicard/2-cards/test_qwen3_moe_routing_replay.py
|
|
estimated_time: 1050
|
|
- name: tests/e2e/multicard/2-cards/test_single_request_aclgraph.py
|
|
estimated_time: 215
|
|
- name: tests/e2e/multicard/2-cards/test_disaggregated_encoder.py
|
|
estimated_time: 90
|
|
- name: tests/e2e/multicard/2-cards/test_sp_pass.py
|
|
estimated_time: 300
|
|
|
|
e2e-multicard-4-cards:
|
|
# TODO: recover skipped tests
|
|
- name: tests/e2e/multicard/4-cards/test_qwen3_next.py
|
|
estimated_time: 1250
|
|
- name: tests/e2e/multicard/4-cards/test_qwen3_5.py
|
|
estimated_time: 60
|
|
- name: tests/e2e/multicard/4-cards/test_data_parallel_tp2.py
|
|
estimated_time: 60
|
|
- name: tests/e2e/multicard/4-cards/test_kimi_k2.py
|
|
estimated_time: 100
|
|
- name: tests/e2e/multicard/4-cards/long_sequence/test_accuracy.py
|
|
estimated_time: 60
|
|
- name: tests/e2e/multicard/4-cards/long_sequence/test_basic.py
|
|
estimated_time: 60
|
|
- name: tests/e2e/multicard/4-cards/long_sequence/test_chunked_prefill_cp.py
|
|
estimated_time: 60
|
|
- name: tests/e2e/multicard/4-cards/long_sequence/test_prefix_caching_cp.py
|
|
estimated_time: 60
|
|
- name: tests/e2e/multicard/4-cards/long_sequence/test_mtp.py
|
|
estimated_time: 60
|
|
is_skipped: true
|
|
- name: tests/e2e/multicard/4-cards/spec_decode/test_mtp_qwen3_next.py
|
|
estimated_time: 60
|