From 27d0be09ce6101342f216dcfecb62ee7875a9c84 Mon Sep 17 00:00:00 2001 From: Tianrui 'Hudayday' Hu <32944717+Hudayday@users.noreply.github.com> Date: Wed, 28 Oct 2026 19:50:05 -0700 Subject: [PATCH] [https://nvbugs/6985375][test] Remove waiver for the mixed-precision retained-dtype test The test broke on main on 2026-10-24 by a merge race: #20167 started reading model_config.sparse_attention_config unconditionally three hours before #20452 merged with a config stub that lacked the field. #18843 added the field to the stub on 2026-10-26, so the test passes on main again and the waiver added by #20927 is no longer needed. Signed-off-by: Tianrui 'Hudayday' Hu <32944717+Hudayday@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 cac8f717778a..8b6b3be485e4 100644 --- a/tests/integration/test_lists/waives.txt +++ b/tests/integration/test_lists/waives.txt @@ -145,7 +145,6 @@ unittest/_torch/attention/multi_gpu/test_mha_helix.py::test_mha_helix_distribute unittest/_torch/attention/multi_gpu/test_mha_helix.py::test_mha_helix_distributed[nccl-scenario: Scenario(dtype=torch.bfloat16, kv_cache_dtype=torch.bfloat16, num_layers=1, num_heads=16, num_kv_heads=4, head_dim=128, hidden_size=2048, rope_theta=10000.0, kv_cache_tokens_per_block=32, bias=False, batch=1, ctx_len=512, atol=0.1, rtol=0.05)] SKIP (https://nvbugs/6991647) unittest/_torch/attention/multi_gpu/test_mha_helix.py::test_mha_helix_distributed[nccl-scenario: Scenario(dtype=torch.bfloat16, kv_cache_dtype=torch.bfloat16, num_layers=1, num_heads=16, num_kv_heads=4, head_dim=128, hidden_size=2048, rope_theta=10000.0, kv_cache_tokens_per_block=32, bias=False, batch=1, ctx_len=64, atol=0.1, rtol=0.05)] SKIP (https://nvbugs/6991647) unittest/_torch/attention/test_attention_mla.py::test_attention_mla SKIP (https://nvbugs/6862662) -unittest/_torch/attention/test_mixed_precision_backends.py::test_mixed_precision_retained_dtype_must_match_model_dtype SKIP (https://nvbugs/6985375) 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)