From 672b8151207f18e0cc5b49c1052dc9341d74352d Mon Sep 17 00:00:00 2001 From: trtllm-agent <296075020+trtllm-agent@users.noreply.github.com> Date: Fri, 31 Jul 2026 16:05:26 -0700 Subject: [PATCH] [nvbugs/6541322][fix] Unwaive fixed Qwen3-Next test The V2 Mamba state pool ValueError was fixed by 7f7dccf991 (KVCacheManagerV2 C++ translation, #14047), which added an SSM min-slot floor in _build_cache_config using the same expression as the live/dummy-slot check it guards, so the pool can no longer be sized below that floor. Remove the now-stale waiver for test_bf16_4gpu[dep4]. The sibling test_nvfp4[tp1_block_reuse-cutlass] waiver is left in place: it has an independent root cause tracked separately under nvbugs/6535767. Signed-off-by: trtllm-agent <296075020+trtllm-agent@users.noreply.github.com> --- 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 1c7212ea9093..78967b6126a8 100644 --- a/tests/integration/test_lists/waives.txt +++ b/tests/integration/test_lists/waives.txt @@ -89,7 +89,6 @@ accuracy/test_llm_api_pytorch.py::TestMiniMaxM2::test_4gpus[attention_dp=False-c accuracy/test_llm_api_pytorch.py::TestNemotronV3Super::test_nvfp4_parallelism[TP4_PP2] SKIP (https://nvbugs/6427411) accuracy/test_llm_api_pytorch.py::TestNemotronV3Ultra::test_nvfp4_4gpus_static_eplb[moe_backend=CUTLASS] SKIP (https://nvbugs/6535767) accuracy/test_llm_api_pytorch.py::TestNemotronV3Ultra::test_nvfp4_parallelism[ADP2_PP2] SKIP (https://nvbugs/6427411) -accuracy/test_llm_api_pytorch.py::TestQwen3NextInstruct::test_bf16_4gpu[dep4] SKIP (https://nvbugs/6535767) accuracy/test_llm_api_pytorch.py::TestQwen3NextInstruct::test_nvfp4[tp1_block_reuse-cutlass] SKIP (https://nvbugs/6535767) accuracy/test_llm_api_pytorch.py::TestQwen3_235B_A22B::test_fp8[latency] SKIP (https://nvbugs/6177390) accuracy/test_llm_api_pytorch.py::TestQwen3_235B_A22B::test_fp8[throughput_latency] SKIP (https://nvbugs/6177390)