From 718a2091d715651db86377ad95e461eef02619fa Mon Sep 17 00:00:00 2001 From: Yao Yao Date: Thu, 20 Aug 2026 04:41:11 +0000 Subject: [PATCH] [TRTLLM-15011][infra] Unwaive TestDeepSeekV4Flash::test_auto_dtype The test was waived for https://nvbugs/6561677, which failed teardown with "SlotAllocator::finishShrink: cannot finish shrink yet" because pages were still occupied when the pool group shrank to zero. That is the same root cause as https://nvbugs/6553427 (TestQwen3_5_35B_A3B::test_fp8[enable_block_reuse=True], "shrink can't be finished"): the KV cache manager tore down while requests were still open, so KvCache objects outlived the manager. PR #17163 drains in-flight requests before clearing the reuse state and guards clearReusableBlocks()/shutdown() against live caches. 6553427 was never waived and is already closed as fixed; this removes the remaining waive. Signed-off-by: Yao Yao --- 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 c390be881c5c..828b6d209b8d 100644 --- a/tests/integration/test_lists/waives.txt +++ b/tests/integration/test_lists/waives.txt @@ -27,7 +27,6 @@ accuracy/test_llm_api_pytorch.py::TestDeepSeekV3Lite::test_bfloat16_4gpus[tp2pp2 accuracy/test_llm_api_pytorch.py::TestDeepSeekV3Lite::test_bfloat16_4gpus[tp4-mtp_nextn=2-attention_dp=True-cuda_graph=True-overlap_scheduler=True-torch_compile=True] SKIP (https://nvbugs/6198774) accuracy/test_llm_api_pytorch.py::TestDeepSeekV3Lite::test_bfloat16_python_scheduler[mtp_nextn=0-attention_dp=False-cuda_graph=False-overlap_scheduler=False-enable_chunked_prefill=True] SKIP (https://nvbugs/6388139) accuracy/test_llm_api_pytorch.py::TestDeepSeekV3Lite::test_bfloat16_python_scheduler[mtp_nextn=2-attention_dp=False-cuda_graph=False-overlap_scheduler=False-enable_chunked_prefill=True] SKIP (https://nvbugs/6507095) -accuracy/test_llm_api_pytorch.py::TestDeepSeekV4Flash::test_auto_dtype SKIP (https://nvbugs/6561677) accuracy/test_llm_api_pytorch.py::TestDeepSeekV4ProDSpark::test_gsm8k_dep8_megamoe_deepgemm SKIP (https://nvbugs/6581063) accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_eagle3_4gpus[v2_kv_cache-cutlass-one_model-no_overlap_scheduler] SKIP (https://nvbugs/6644462) accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_eagle3_guided_decoding_4gpus[one_model] SKIP (https://nvbugs/5596343)