From 0a4b177ab19797dbfb98fd0417820e046dd47129 Mon Sep 17 00:00:00 2001 From: Brian Nguyen Date: Fri, 28 Aug 2026 07:21:48 -0700 Subject: [PATCH] [https://nvbugs/6669206][test] Unwaive test_kimi_k3_gen_dep[1] fixed by #18226 The Kimi K3 MLA decode backend-selection defect behind this failure was fixed in #18226 (keep CuTe-DSL MLA decode for H=96 speculative-verify batches). Remove the now-stale waiver so unittest/tools/test_layer_wise_benchmarks.py::test_kimi_k3_gen_dep[1] runs again on B200. Verified locally on B200 with the fix present: the test passes (1 passed, ~105s). 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 532f824b9ae0..2a0e647e8f2e 100644 --- a/tests/integration/test_lists/waives.txt +++ b/tests/integration/test_lists/waives.txt @@ -363,7 +363,6 @@ unittest/llmapi/test_llm_multi_gpu_pytorch.py::test_llm_get_stats_pp2[False-Fals unittest/llmapi/test_llm_pytorch.py::test_gqa_nemo_lora[None] SKIP (https://nvbugs/6162504) unittest/llmapi/test_llm_pytorch.py::test_gqa_nemo_lora[cuda_graph_config0] SKIP (https://nvbugs/6162504) unittest/llmapi/test_memory_profiling.py::test_profile_kvcache SKIP (https://nvbugs/5580781) -unittest/tools/test_layer_wise_benchmarks.py::test_kimi_k3_gen_dep[1] SKIP (https://nvbugs/6669206) verl/test_verl_cases.py::test_async_generate SKIP (https://nvbugs/6683838) verl/test_verl_cases.py::test_async_memory_management SKIP (https://nvbugs/6683838) verl/test_verl_cases.py::test_init_without_device_mesh SKIP (https://nvbugs/6683838)