From 0823107448722b0f0c648c01874dcd385c308c68 Mon Sep 17 00:00:00 2001 From: Lizhi Zhou <1432185+reasonsolo@users.noreply.github.com> Date: Thu, 18 Dec 2025 21:40:05 -0800 Subject: [PATCH] unwaive test and remove test_auto_scaling tests to speed up L0 Signed-off-by: Lizhi Zhou <1432185+reasonsolo@users.noreply.github.com> --- tests/integration/test_lists/qa/llm_function_core_sanity.txt | 5 +++++ tests/integration/test_lists/test-db/l0_dgx_h100.yml | 5 ----- tests/integration/test_lists/waives.txt | 1 - 3 files changed, 5 insertions(+), 6 deletions(-) diff --git a/tests/integration/test_lists/qa/llm_function_core_sanity.txt b/tests/integration/test_lists/qa/llm_function_core_sanity.txt index 20f732b7163..cbe795945ee 100644 --- a/tests/integration/test_lists/qa/llm_function_core_sanity.txt +++ b/tests/integration/test_lists/qa/llm_function_core_sanity.txt @@ -247,6 +247,11 @@ disaggregated/test_workers.py::test_workers_conditional_disaggregation[TinyLlama disaggregated/test_workers.py::test_workers_kv_cache_aware_router_eviction[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_events[TinyLlama-1.1B-Chat-v1.0] +disaggregated/test_auto_scaling.py::test_service_discovery[etcd-load_balancing] +disaggregated/test_auto_scaling.py::test_service_discovery[http-load_balancing] +disaggregated/test_auto_scaling.py::test_worker_restart[etcd-round_robin] +disaggregated/test_auto_scaling.py::test_worker_restart[http-round_robin] +disaggregated/test_auto_scaling.py::test_worker_restart[http-kv_cache_aware] test_e2e.py::test_openai_chat_harmony test_e2e.py::test_openai_consistent_chat test_e2e.py::test_openai_multi_chat_example diff --git a/tests/integration/test_lists/test-db/l0_dgx_h100.yml b/tests/integration/test_lists/test-db/l0_dgx_h100.yml index 4e90db0050b..25c5ac3aeaa 100644 --- a/tests/integration/test_lists/test-db/l0_dgx_h100.yml +++ b/tests/integration/test_lists/test-db/l0_dgx_h100.yml @@ -116,17 +116,12 @@ l0_dgx_h100: - accuracy/test_disaggregated_serving.py::TestLlama3_1_8BInstruct::test_multi_instance[MMLU] - accuracy/test_llm_api_pytorch.py::TestQwen3NextInstruct::test_bf16_4gpu[tp4ep4_cudagraph_overlap] - disaggregated/test_auto_scaling.py::test_service_discovery[etcd-round_robin] - - disaggregated/test_auto_scaling.py::test_service_discovery[etcd-load_balancing] - - disaggregated/test_auto_scaling.py::test_worker_restart[etcd-round_robin] - disaggregated/test_auto_scaling.py::test_worker_restart[etcd-load_balancing] - disaggregated/test_auto_scaling.py::test_minimal_instances[etcd-round_robin] - disaggregated/test_auto_scaling.py::test_disagg_server_restart[etcd-round_robin] - disaggregated/test_auto_scaling.py::test_service_discovery[http-round_robin] - - disaggregated/test_auto_scaling.py::test_service_discovery[http-load_balancing] - disaggregated/test_auto_scaling.py::test_service_discovery[http-kv_cache_aware] - - disaggregated/test_auto_scaling.py::test_worker_restart[http-round_robin] - disaggregated/test_auto_scaling.py::test_worker_restart[http-load_balancing] - - disaggregated/test_auto_scaling.py::test_worker_restart[http-kv_cache_aware] - disaggregated/test_auto_scaling.py::test_minimal_instances[http-round_robin] - disaggregated/test_auto_scaling.py::test_disagg_server_restart[http-round_robin] - condition: diff --git a/tests/integration/test_lists/waives.txt b/tests/integration/test_lists/waives.txt index 4f6d8e75a44..c3a43724914 100644 --- a/tests/integration/test_lists/waives.txt +++ b/tests/integration/test_lists/waives.txt @@ -476,7 +476,6 @@ accuracy/test_llm_api_pytorch.py::TestLlama4ScoutInstruct::test_fp4_chunked_pref accuracy/test_llm_api_pytorch.py::TestLlama4ScoutInstruct::test_fp4[tp4-cuda_graph=True] SKIP (https://nvbugs/5702793) disaggregated/test_auto_scaling.py::test_minimal_instances[etcd-round_robin] SKIP (https://nvbugs/5748564) disaggregated/test_auto_scaling.py::test_minimal_instances[http-round_robin] SKIP (https://nvbugs/5755963) -unittest/llmapi/apps/test_disagg_serving_perf_metrics.py SKIP (https://nvbugs/5752516) unittest/_torch/attention/test_trtllm_flashinfer_symbol_collision.py::test_flashinfer_fused_moe_matches_torch_moe SKIP (https://nvbugs/5752521) unittest/llmapi/apps/_test_openai_responses.py::test_reasoning_effort[DeepSeek-R1-Distill-Qwen-1.5B] SKIP (https://nvbugs/5753250) unittest/llmapi/apps/_test_openai_responses.py::test_multi_turn_chat[Qwen3/Qwen3-0.6B] SKIP (https://nvbugs/5753250)