From 77cf28516e22eb5d30320bc71f5e4af47010fb3e Mon Sep 17 00:00:00 2001 From: Brian Nguyen Date: Mon, 21 Sep 2026 23:41:12 -0500 Subject: [PATCH 1/2] [None][ci] Replace blanket unittest/_torch/executor waive with per-test waives The directory-level waive added in #19381 for https://nvbugs/6800103 was left in place after #19382 fixed that bug, so every test under unittest/_torch/executor has been skipped in CI since 2026-09-18. Running the tree on main with the line removed gives 2436 passed and 54 failed. Replace the blanket entry with waives for exactly the failing tests, so the rest of the tree runs again: - test_kv_cache_budget_split.py: class-level waives for TestSplitGpuBudgetForDraft and TestExternalDrafterKvDtype, tracked under the existing https://nvbugs/6800223 (same stale-fixture cause). - test_mamba_cache_manager.py: 16 test functions whose fixture lacks the `mapping` attribute production now reads. - test_kv_cache_v2_vocab_size.py: 11 parametrizations whose fixture lacks `_max_cuda_graph_batch_size`. - test_pytorch_model_engine.py: test_prepare_tp_inputs_with_helix_parallelism, base update_helix_param signature lacks helix_owned_new_tokens. The last three are tracked under https://nvbugs/6818710. Signed-off-by: Brian Nguyen --- tests/integration/test_lists/waives.txt | 31 ++++++++++++++++++++++++- 1 file changed, 30 insertions(+), 1 deletion(-) diff --git a/tests/integration/test_lists/waives.txt b/tests/integration/test_lists/waives.txt index 0c5e5c889af9..887055da144d 100644 --- a/tests/integration/test_lists/waives.txt +++ b/tests/integration/test_lists/waives.txt @@ -245,8 +245,37 @@ test_e2e.py::test_ptp_quickstart_bert[TRTLLM-BertForSequenceClassification-bert/ test_e2e.py::test_ptp_quickstart_bert[VANILLA-BertForSequenceClassification-bert/bert-base-uncased-yelp-polarity] SKIP (bug pending, tracked in PR 17414) unittest/_torch/attention/sparse/dsa/test_req_idx_per_token.py::test_on_update_kv_lens_rebuilds_stale_map SKIP (https://nvbugs/6574939) unittest/_torch/attention/test_attention_backends.py::test_attention_backend[qwen2_0_5b_gqa_hd64-ctx-bf16-HND-p32-v1] SKIP (https://nvbugs/6641268) -unittest/_torch/executor SKIP (https://nvbugs/6800103) +unittest/_torch/executor/kv_cache/test_kv_cache_budget_split.py::TestExternalDrafterKvDtype SKIP (https://nvbugs/6800223) +unittest/_torch/executor/kv_cache/test_kv_cache_budget_split.py::TestSplitGpuBudgetForDraft SKIP (https://nvbugs/6800223) unittest/_torch/executor/kv_cache/test_kv_cache_budget_split.py::TestSplitGpuBudgetForDraft::test_target_cost_uses_derived_layer_type_windows SKIP (https://nvbugs/6800223) +unittest/_torch/executor/kv_cache/test_kv_cache_v2_vocab_size.py::test_branch_only_enables_multimodal_keys_when_needed[dense-encoder_disable_noop] SKIP (https://nvbugs/6818710) +unittest/_torch/executor/kv_cache/test_kv_cache_v2_vocab_size.py::test_branch_only_enables_multimodal_keys_when_needed[dense-multimodal] SKIP (https://nvbugs/6818710) +unittest/_torch/executor/kv_cache/test_kv_cache_v2_vocab_size.py::test_branch_only_enables_multimodal_keys_when_needed[dense-text_only] SKIP (https://nvbugs/6818710) +unittest/_torch/executor/kv_cache/test_kv_cache_v2_vocab_size.py::test_branch_only_enables_multimodal_keys_when_needed[nemotron_hybrid-encoder_disable_noop] SKIP (https://nvbugs/6818710) +unittest/_torch/executor/kv_cache/test_kv_cache_v2_vocab_size.py::test_branch_only_enables_multimodal_keys_when_needed[nemotron_hybrid-multimodal] SKIP (https://nvbugs/6818710) +unittest/_torch/executor/kv_cache/test_kv_cache_v2_vocab_size.py::test_branch_only_enables_multimodal_keys_when_needed[nemotron_hybrid-text_only] SKIP (https://nvbugs/6818710) +unittest/_torch/executor/kv_cache/test_kv_cache_v2_vocab_size.py::test_branch_only_enables_multimodal_keys_when_needed[qwen3_5_hybrid-encoder_disable_noop] SKIP (https://nvbugs/6818710) +unittest/_torch/executor/kv_cache/test_kv_cache_v2_vocab_size.py::test_branch_only_enables_multimodal_keys_when_needed[qwen3_5_hybrid-multimodal] SKIP (https://nvbugs/6818710) +unittest/_torch/executor/kv_cache/test_kv_cache_v2_vocab_size.py::test_branch_only_enables_multimodal_keys_when_needed[qwen3_5_hybrid-text_only] SKIP (https://nvbugs/6818710) +unittest/_torch/executor/kv_cache/test_kv_cache_v2_vocab_size.py::test_unresolvable_vocab_size_only_warns_when_multimodal_keys_are_needed[False] SKIP (https://nvbugs/6818710) +unittest/_torch/executor/kv_cache/test_kv_cache_v2_vocab_size.py::test_unresolvable_vocab_size_only_warns_when_multimodal_keys_are_needed[True] SKIP (https://nvbugs/6818710) +unittest/_torch/executor/kv_cache/test_mamba_cache_manager.py::test_hybrid_cache_manager_factory_honors_v2_setting SKIP (https://nvbugs/6818710) +unittest/_torch/executor/kv_cache/test_mamba_cache_manager.py::test_hybrid_cache_manager_factory_keeps_v1_disagg_route SKIP (https://nvbugs/6818710) +unittest/_torch/executor/kv_cache/test_mamba_cache_manager.py::test_hybrid_cache_manager_factory_rejects_cpp_preference_with_explicit_v2 SKIP (https://nvbugs/6818710) +unittest/_torch/executor/kv_cache/test_mamba_cache_manager.py::test_hybrid_cache_manager_factory_rejects_mixed_override_with_reuse SKIP (https://nvbugs/6818710) +unittest/_torch/executor/kv_cache/test_mamba_cache_manager.py::test_hybrid_cache_manager_factory_rejects_python_v1_disagg_reuse SKIP (https://nvbugs/6818710) +unittest/_torch/executor/kv_cache/test_mamba_cache_manager.py::test_hybrid_cache_manager_factory_rejects_unsupported_v2_disagg_route SKIP (https://nvbugs/6818710) +unittest/_torch/executor/kv_cache/test_mamba_cache_manager.py::test_hybrid_cache_manager_factory_routes_explicit_v2_disagg SKIP (https://nvbugs/6818710) +unittest/_torch/executor/kv_cache/test_mamba_cache_manager.py::test_hybrid_cache_manager_factory_v2_preference_does_not_select_v2 SKIP (https://nvbugs/6818710) +unittest/_torch/executor/kv_cache/test_mamba_cache_manager.py::test_kimi_disagg_python_nixl_routes_to_mixed_manager SKIP (https://nvbugs/6818710) +unittest/_torch/executor/kv_cache/test_mamba_cache_manager.py::test_kimi_disagg_rejects_non_python_transceiver_route SKIP (https://nvbugs/6818710) +unittest/_torch/executor/kv_cache/test_mamba_cache_manager.py::test_kimi_explicit_v2_manager_enables_kda_replay SKIP (https://nvbugs/6818710) +unittest/_torch/executor/kv_cache/test_mamba_cache_manager.py::test_kimi_explicit_v2_manager_geometry SKIP (https://nvbugs/6818710) +unittest/_torch/executor/kv_cache/test_mamba_cache_manager.py::test_kimi_explicit_v2_manager_uses_qkv_convolution_layout SKIP (https://nvbugs/6818710) +unittest/_torch/executor/kv_cache/test_mamba_cache_manager.py::test_kimi_without_v2_preference_uses_mixed_manager SKIP (https://nvbugs/6818710) +unittest/_torch/executor/kv_cache/test_mamba_cache_manager.py::test_qwen3_gdn_replay_uses_v2_preference SKIP (https://nvbugs/6818710) +unittest/_torch/executor/test_pytorch_model_engine.py::PyTorchModelEngineTestCase::test_prepare_tp_inputs_with_helix_parallelism SKIP (https://nvbugs/6818710) +unittest/_torch/modeling/test_gemma4_e2e_dummy.py::test_e2e_text_31b_dummy SKIP (https://nvbugs/6607482) unittest/_torch/modeling/test_modeling_nemotron_h_multimodal.py::test_nemotron_nano_v2_vl_image_batch_equivalence SKIP (https://nvbugs/6758946) unittest/_torch/modeling/test_modeling_nemotron_h_multimodal.py::test_nemotron_nano_v2_vl_video_batch_equivalence SKIP (https://nvbugs/6625695) unittest/_torch/modules/tests_lora_modules/test_nemotron_h_lora_sanity.py::TestNemotronHLoRA::test_lora_pp2_sanity SKIP (https://nvbugs/6428124) From e536a60695189f96ee3112030eefcd78f1c7244f Mon Sep 17 00:00:00 2001 From: Brian Nguyen Date: Tue, 22 Sep 2026 04:58:36 +0000 Subject: [PATCH 2/2] Address trivial review comments Signed-off-by: Brian Nguyen --- tests/integration/test_lists/waives.txt | 1 - 1 file changed, 1 deletion(-) diff --git a/tests/integration/test_lists/waives.txt b/tests/integration/test_lists/waives.txt index 887055da144d..b9108db795f3 100644 --- a/tests/integration/test_lists/waives.txt +++ b/tests/integration/test_lists/waives.txt @@ -247,7 +247,6 @@ unittest/_torch/attention/sparse/dsa/test_req_idx_per_token.py::test_on_update_k unittest/_torch/attention/test_attention_backends.py::test_attention_backend[qwen2_0_5b_gqa_hd64-ctx-bf16-HND-p32-v1] SKIP (https://nvbugs/6641268) unittest/_torch/executor/kv_cache/test_kv_cache_budget_split.py::TestExternalDrafterKvDtype SKIP (https://nvbugs/6800223) unittest/_torch/executor/kv_cache/test_kv_cache_budget_split.py::TestSplitGpuBudgetForDraft SKIP (https://nvbugs/6800223) -unittest/_torch/executor/kv_cache/test_kv_cache_budget_split.py::TestSplitGpuBudgetForDraft::test_target_cost_uses_derived_layer_type_windows SKIP (https://nvbugs/6800223) unittest/_torch/executor/kv_cache/test_kv_cache_v2_vocab_size.py::test_branch_only_enables_multimodal_keys_when_needed[dense-encoder_disable_noop] SKIP (https://nvbugs/6818710) unittest/_torch/executor/kv_cache/test_kv_cache_v2_vocab_size.py::test_branch_only_enables_multimodal_keys_when_needed[dense-multimodal] SKIP (https://nvbugs/6818710) unittest/_torch/executor/kv_cache/test_kv_cache_v2_vocab_size.py::test_branch_only_enables_multimodal_keys_when_needed[dense-text_only] SKIP (https://nvbugs/6818710)