kanshan/TensorRT-LLMs
1
0
Fork 0
mirror of https://github.com/NVIDIA/TensorRT-LLM.git synced 2026-02-12 05:53:33 +08:00
Code Issues Actions 1 Packages Projects Releases Wiki Activity

Waive dynamic spec decode unit test

Browse Source 
Signed-off-by: Zheyu Fu <zheyuf@NVIDIA.com>
This commit is contained in:
Zheyu Fu 2025-12-20 01:18:16 +00:00
parent 7c638f155b
commit ab45d6a7c7
2 changed files with 2 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
tests/integration/test_lists/waives.txt
View File

@ -481,3 +481,4 @@ unittest/llmapi/apps/test_disagg_serving_perf_metrics.py SKIP (https://nvbugs/57
unittest/_torch/attention/test_trtllm_flashinfer_symbol_collision.py::test_flashinfer_fused_moe_matches_torch_moe SKIP (https://nvbugs/5752521)
unittest/llmapi/apps/_test_openai_responses.py::test_reasoning_effort[DeepSeek-R1-Distill-Qwen-1.5B] SKIP (https://nvbugs/5753250)
unittest/llmapi/apps/_test_openai_responses.py::test_multi_turn_chat[Qwen3/Qwen3-0.6B] SKIP (https://nvbugs/5753250)
unittest/_torch/speculative/test_dynamic_spec_decode.py::test_dynamic_spec_decode SKIP (https://nvbugs/5758449)

1
tests/unittest/_torch/speculative/test_dynamic_spec_decode.py
View File

@ -21,6 +21,7 @@ def enforce_single_worker(monkeypatch):
yield
@pytest.mark.skip("https://nvbugs/5758449")
@pytest.mark.parametrize("disable_overlap_scheduler", [True, False])
@pytest.mark.high_cuda_memory
def test_dynamic_spec_decode(enforce_single_worker,