[None][ci] move some test cases from H100 to A10 (#8449)

QiJune · web-flow · commit d05079ba4b19 · 2025-10-20T01:58:34.000-04:00
Signed-off-by: junq &lt;22017000+QiJune@users.noreply.github.com&gt;
diff --git a/jenkins/L0_Test.groovy b/jenkins/L0_Test.groovy
@@ -2432,14 +2432,14 @@ def launchTestJobs(pipeline, testFilter)
         "DGX_H100-4_GPUs-PyTorch-Others-1": ["dgx-h100-x4", "l0_dgx_h100", 1, 1, 4],
         "DGX_H100-2_GPUs-PyTorch-Ray-1": ["dgx-h100-x2", "l0_dgx_h100", 1, 1, 2],
         "DGX_H100-4_GPUs-CPP-1": ["dgx-h100-x4", "l0_dgx_h100", 1, 1, 4],
-        "A10-PyTorch-1": ["a10", "l0_a10", 1, 1],
+        "A10-PyTorch-1": ["a10", "l0_a10", 1, 2],
+        "A10-PyTorch-2": ["a10", "l0_a10", 2, 2],
         "A10-CPP-1": ["a10", "l0_a10", 1, 1],
-        "A10-TensorRT-1": ["a10", "l0_a10", 1, 6],
-        "A10-TensorRT-2": ["a10", "l0_a10", 2, 6],
-        "A10-TensorRT-3": ["a10", "l0_a10", 3, 6],
-        "A10-TensorRT-4": ["a10", "l0_a10", 4, 6],
-        "A10-TensorRT-5": ["a10", "l0_a10", 5, 6],
-        "A10-TensorRT-6": ["a10", "l0_a10", 6, 6],
+        "A10-TensorRT-1": ["a10", "l0_a10", 1, 5],
+        "A10-TensorRT-2": ["a10", "l0_a10", 2, 5],
+        "A10-TensorRT-3": ["a10", "l0_a10", 3, 5],
+        "A10-TensorRT-4": ["a10", "l0_a10", 4, 5],
+        "A10-TensorRT-5": ["a10", "l0_a10", 5, 5],
         "A10-Pybind": ["a10", "l0_a10_pybind", 1, 1],
         "A30-Triton-1": ["a30", "l0_a30", 1, 1],
         "A30-PyTorch-1": ["a30", "l0_a30", 1, 2],
diff --git a/tests/integration/test_lists/test-db/l0_a10.yml b/tests/integration/test_lists/test-db/l0_a10.yml
@@ -21,12 +21,30 @@ l0_a10:
   # test list either).
   - unittest/_torch/models/checkpoints/hf/test_weight_loader.py
   - unittest/others/test_time_breakdown.py
+  - unittest/disaggregated/test_disagg_utils.py
+  - unittest/disaggregated/test_router.py
+  - unittest/disaggregated/test_remoteDictionary.py
+  - unittest/disaggregated/test_disagg_cluster_manager_worker.py
+  - unittest/disaggregated/test_cluster_storage.py
   - disaggregated/test_disaggregated.py::test_disaggregated_single_gpu_with_mpirun[TinyLlama-1.1B-Chat-v1.0]
   - disaggregated/test_disaggregated.py::test_disaggregated_single_gpu_with_mpirun_trt_backend[TinyLlama-1.1B-Chat-v1.0]
   - disaggregated/test_disaggregated.py::test_disaggregated_cuda_graph[TinyLlama-1.1B-Chat-v1.0]
   - disaggregated/test_disaggregated.py::test_disaggregated_mixed[TinyLlama-1.1B-Chat-v1.0]
   - disaggregated/test_disaggregated.py::test_disaggregated_overlap[TinyLlama-1.1B-Chat-v1.0]
   - disaggregated/test_disaggregated.py::test_disaggregated_diff_max_tokens[TinyLlama-1.1B-Chat-v1.0]
+  - disaggregated/test_disaggregated.py::test_disaggregated_kv_cache_time_output[TinyLlama-1.1B-Chat-v1.0]
+  - disaggregated/test_disaggregated.py::test_disaggregated_perf_metrics[TinyLlama-1.1B-Chat-v1.0]
+  - disaggregated/test_disaggregated.py::test_disaggregated_cache_aware_balance[TinyLlama-1.1B-Chat-v1.0]
+  - disaggregated/test_disaggregated.py::test_disaggregated_conditional[TinyLlama-1.1B-Chat-v1.0]
+  - disaggregated/test_disaggregated.py::test_disaggregated_ngram[TinyLlama-1.1B-Chat-v1.0]
+  - disaggregated/test_workers.py::test_workers_conditional_disaggregation[TinyLlama-1.1B-Chat-v1.0]
+  - disaggregated/test_workers.py::test_workers_kv_cache_events[TinyLlama-1.1B-Chat-v1.0]
+  - disaggregated/test_workers.py::test_workers_kv_cache_aware_router[TinyLlama-1.1B-Chat-v1.0]
+  - disaggregated/test_workers.py::test_workers_kv_cache_aware_router_eviction[TinyLlama-1.1B-Chat-v1.0]
+  - disaggregated/test_disaggregated_single_gpu.py::test_disaggregated_simple_llama[False-False-TinyLlama-1.1B-Chat-v1.0]
+  - disaggregated/test_disaggregated_single_gpu.py::test_disaggregated_simple_llama[False-True-TinyLlama-1.1B-Chat-v1.0]
+  - disaggregated/test_disaggregated_single_gpu.py::test_disaggregated_simple_llama[True-False-TinyLlama-1.1B-Chat-v1.0]
+  - disaggregated/test_disaggregated_single_gpu.py::test_disaggregated_simple_llama[True-True-TinyLlama-1.1B-Chat-v1.0]
   - test_e2e.py::test_openai_chat_guided_decoding
   - test_e2e.py::test_openai_chat_multimodal_example
   - test_e2e.py::test_openai_perf_metrics
@@ -92,7 +110,6 @@ l0_a10:
   - examples/test_bert.py::test_llm_bert_general[compare_hf-enable_remove_input_padding-use_attention_plugin-enable_context_fmha-tp:1-pp:1-float16-BertModel-bert/bert-base-uncased]
   - unittest/trt/model/test_mistral.py
   - unittest/trt/model/test_llama.py
-  - test_e2e.py::test_gpt3_175b_1layers_build_only # 6 mins
   - llmapi/test_llm_api_connector.py::test_connector_simple[True]
   - llmapi/test_llm_api_connector.py::test_connector_simple[False]
   - llmapi/test_llm_api_connector.py::test_connector_async_onboard[True]
@@ -119,7 +136,6 @@ l0_a10:
   - test_e2e.py::test_trtllm_bench_sanity[--non-streaming-FP16-meta-llama/Llama-3.1-8B-llama-3.1-model/Meta-Llama-3.1-8B]
   - test_e2e.py::test_trtllm_bench_latency_sanity[FP16-meta-llama/Llama-3.1-8B-llama-3.1-model/Meta-Llama-3.1-8B]
   - unittest/trt/quantization
-  - accuracy/test_cli_flow.py::TestLlama7B::test_streamingllm # 2 mins
   - unittest/trt/functional # 37 mins
   - llmapi/test_llm_examples.py::test_llmapi_quickstart_atexit
   - unittest/api_stability
@@ -140,13 +156,9 @@ l0_a10:
   - accuracy/test_cli_flow.py::TestVicuna7B::test_eagle_2[cuda_graph=True-chunked_context=False] # 5 mins
   - accuracy/test_cli_flow.py::TestVicuna7B::test_eagle_2[cuda_graph=True-chunked_context=True] # 5 mins
   - accuracy/test_cli_flow.py::TestLlama2_7B::test_auto_dtype
-  - examples/test_chatglm.py::test_llm_glm_4_9b_single_gpu_summary[glm-4-9b-disable_weight_only]
   - unittest/trt/attention/test_gpt_attention_IFB.py
   - unittest/trt/attention/test_gpt_attention_no_cache.py
-  - unittest/trt/model/test_mamba.py # 3 mins
   - examples/test_whisper.py::test_llm_whisper_general[large-v3-disable_gemm_plugin-enable_attention_plugin-disable_weight_only-float16-nb:1-use_cpp_runtime]
-  - examples/test_mamba.py::test_llm_mamba_1gpu[mamba2-130m-float16-enable_gemm_plugin]
-  - examples/test_mamba.py::test_llm_mamba_1gpu[mamba-codestral-7B-v0.1-float16-enable_gemm_plugin] # 3 mins
 - condition:
     ranges:
       system_gpu_count:
@@ -205,6 +217,12 @@ l0_a10:
   - accuracy/test_llm_api.py::TestEagle2Vicuna_7B_v1_3::test_auto_dtype
   - stress_test/stress_test.py::test_run_stress_test[llama-v3-8b-instruct-hf_tp1-stress_time_300s_timeout_450s-MAX_UTILIZATION-trt-stress-test]
   - stress_test/stress_test.py::test_run_stress_test[llama-v3-8b-instruct-hf_tp1-stress_time_300s_timeout_450s-GUARANTEED_NO_EVICT-trt-stress-test]
+  - test_e2e.py::test_gpt3_175b_1layers_build_only # 6 mins
+  - examples/test_chatglm.py::test_llm_glm_4_9b_single_gpu_summary[glm-4-9b-disable_weight_only]
+  - unittest/trt/model/test_mamba.py # 3 mins
+  - examples/test_mamba.py::test_llm_mamba_1gpu[mamba2-130m-float16-enable_gemm_plugin]
+  - examples/test_mamba.py::test_llm_mamba_1gpu[mamba-codestral-7B-v0.1-float16-enable_gemm_plugin] # 3 mins
+  - accuracy/test_cli_flow.py::TestLlama7B::test_streamingllm # 2 mins
 - condition:
     ranges:
       system_gpu_count:
diff --git a/tests/integration/test_lists/test-db/l0_h100.yml b/tests/integration/test_lists/test-db/l0_h100.yml
@@ -32,11 +32,6 @@ l0_h100:
   - unittest/_torch/modeling -k "modeling_nemotron"
   - unittest/_torch/modeling -k "modeling_gemma3"
   - unittest/_torch/modeling -k "modeling_gpt_oss"
-  - unittest/disaggregated/test_disagg_utils.py
-  - unittest/disaggregated/test_router.py
-  - unittest/disaggregated/test_remoteDictionary.py
-  - unittest/disaggregated/test_disagg_cluster_manager_worker.py
-  - unittest/disaggregated/test_cluster_storage.py
   - accuracy/test_llm_api_pytorch.py::TestGemma3_1BInstruct::test_auto_dtype
   - accuracy/test_llm_api_pytorch.py::TestGemma3_1BInstruct::test_auto_dtype_vswa_without_reuse
   - accuracy/test_llm_api_pytorch.py::TestGemma3_1BInstruct::test_auto_dtype_vswa_reuse
@@ -81,15 +76,7 @@ l0_h100:
   - disaggregated/test_disaggregated.py::test_disaggregated_deepseek_v3_lite_fp8_tp1_single_gpu_mtp[DeepSeek-V3-Lite-fp8]
   - disaggregated/test_disaggregated.py::test_disaggregated_deepseek_v3_lite_fp8_tp1_two_mtp[DeepSeek-V3-Lite-fp8]
   - disaggregated/test_disaggregated.py::test_disaggregated_deepseek_v3_lite_fp8_ucx_tp1_single_gpu[DeepSeek-V3-Lite-fp8]
-  - disaggregated/test_disaggregated.py::test_disaggregated_cuda_graph[TinyLlama-1.1B-Chat-v1.0]
-  - disaggregated/test_disaggregated.py::test_disaggregated_kv_cache_time_output[TinyLlama-1.1B-Chat-v1.0]
-  - disaggregated/test_disaggregated.py::test_disaggregated_mixed[TinyLlama-1.1B-Chat-v1.0]
-  - disaggregated/test_disaggregated.py::test_disaggregated_overlap[TinyLlama-1.1B-Chat-v1.0]
-  - disaggregated/test_disaggregated.py::test_disaggregated_perf_metrics[TinyLlama-1.1B-Chat-v1.0]
-  - disaggregated/test_disaggregated_single_gpu.py::test_disaggregated_simple_llama[False-False-TinyLlama-1.1B-Chat-v1.0]
-  - disaggregated/test_disaggregated_single_gpu.py::test_disaggregated_simple_llama[False-True-TinyLlama-1.1B-Chat-v1.0]
-  - disaggregated/test_disaggregated_single_gpu.py::test_disaggregated_simple_llama[True-False-TinyLlama-1.1B-Chat-v1.0]
-  - disaggregated/test_disaggregated_single_gpu.py::test_disaggregated_simple_llama[True-True-TinyLlama-1.1B-Chat-v1.0]
+  - disaggregated/test_disaggregated.py::test_disaggregated_load_balance[TinyLlama-1.1B-Chat-v1.0]
   - disaggregated/test_disaggregated_single_gpu.py::test_disaggregated_simple_deepseek[False-False-DeepSeek-V3-Lite-fp8/fp8]
   - disaggregated/test_disaggregated_single_gpu.py::test_disaggregated_simple_deepseek[False-True-DeepSeek-V3-Lite-fp8/fp8]
   - disaggregated/test_disaggregated_single_gpu.py::test_disaggregated_simple_deepseek[True-False-DeepSeek-V3-Lite-fp8/fp8]
@@ -98,14 +85,6 @@ l0_h100:
   - disaggregated/test_disaggregated_single_gpu.py::test_disaggregated_simple_qwen3[False-True-Qwen3-8B-FP8]
   - disaggregated/test_disaggregated_single_gpu.py::test_disaggregated_simple_qwen3[True-False-Qwen3-8B-FP8]
   - disaggregated/test_disaggregated_single_gpu.py::test_disaggregated_simple_qwen3[True-True-Qwen3-8B-FP8]
-  - disaggregated/test_disaggregated.py::test_disaggregated_load_balance[TinyLlama-1.1B-Chat-v1.0]
-  - disaggregated/test_disaggregated.py::test_disaggregated_cache_aware_balance[TinyLlama-1.1B-Chat-v1.0]
-  - disaggregated/test_disaggregated.py::test_disaggregated_conditional[TinyLlama-1.1B-Chat-v1.0]
-  - disaggregated/test_disaggregated.py::test_disaggregated_ngram[TinyLlama-1.1B-Chat-v1.0]
-  - disaggregated/test_workers.py::test_workers_conditional_disaggregation[TinyLlama-1.1B-Chat-v1.0]
-  - disaggregated/test_workers.py::test_workers_kv_cache_events[TinyLlama-1.1B-Chat-v1.0]
-  - disaggregated/test_workers.py::test_workers_kv_cache_aware_router[TinyLlama-1.1B-Chat-v1.0]
-  - disaggregated/test_workers.py::test_workers_kv_cache_aware_router_eviction[TinyLlama-1.1B-Chat-v1.0]
   - disaggregated/test_disaggregated_single_gpu.py::test_disaggregated_llama_context_capacity[False-False-DeepSeek-V3-Lite-fp8/fp8]
   - disaggregated/test_disaggregated_single_gpu.py::test_disaggregated_spec_dec_batch_slot_limit[True-False-EAGLE3-LLaMA3.1-Instruct-8B-Llama-3.1-8B-Instruct]
   - disaggregated/test_disaggregated_single_gpu.py::test_disaggregated_spec_dec_batch_slot_limit[False-False-EAGLE3-LLaMA3.1-Instruct-8B-Llama-3.1-8B-Instruct]
