kanshan/TensorRT-LLMs
1
0
Fork 0
mirror of https://github.com/NVIDIA/TensorRT-LLM.git synced 2026-01-14 06:27:45 +08:00
Code Issues Actions 1 Packages Projects Releases Wiki Activity

[None][infra] Waive failed tests for release branch 0818 (#6993)

Browse Source 
Signed-off-by: qqiao <qqiao@nvidia.com>
Signed-off-by: Wangshanshan <30051912+dominicshanshan@users.noreply.github.com>
This commit is contained in:
Emma Qiao 2025-08-18 20:31:50 +08:00 committed by Jonas Yang CN
parent f4dc1ed39c
commit 09bca7ca82
2 changed files with 4 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
tests/integration/test_lists/waives.txt
View File

@ -362,3 +362,6 @@ full:GB200/examples/test_qwen.py::test_llm_qwen_7b_multi_gpus_summary[qwen1.5_7b
full:GB200/examples/test_qwen.py::test_llm_qwen_7b_multi_gpus_summary[qwen2_7b_instruct-enable_fmha_fp32_acc-enable_plugin-tp2pp2-nb:4] SKIP (https://nvbugs/5247837)
full:GB200/examples/test_qwen.py::test_llm_qwen_7b_multi_gpus_summary[qwen2_vl_7b_instruct-enable_fmha_fp32_acc-enable_plugin-tp2pp2-nb:4] SKIP (https://nvbugs/5359696)
full:GB200/examples/test_qwen.py::test_llm_qwen_7b_multi_gpus_summary[qwen2.5_7b_chat-enable_fmha_fp32_acc-enable_plugin-tp2pp2-nb:4] SKIP (https://nvbugs/5247837)
accuracy/test_llm_api_pytorch.py::TestMistralSmall24B::test_auto_dtype[/scratch.trt_llm_data/llm-models/Mistral-Small-3.1-24B-Instruct-2503-fp8-FP8] SKIP (https://nvbugs/5462007)
accuracy/test_cli_flow.py::TestLlama3_8BInstructGradient1048k::test_long_context_ppl SKIP (https://nvbugs/5413362)
accuracy/test_llm_api_pytorch.py::TestDeepSeekR1::test_nvfp4_multi_gpus[throughput_tp8] SKIP (https://nvbugs/5455140)

1
tests/unittest/_torch/speculative/test_eagle3.py
View File

@ -16,6 +16,7 @@ from tensorrt_llm.llmapi import (CudaGraphConfig, EagleDecodingConfig,
sys.path.append(os.path.join(os.path.dirname(__file__), '..'))
@pytest.mark.skip(reason="https://nvbugs/5461761")
@pytest.mark.parametrize(
"use_cuda_graph,attn_backend,disable_overlap_scheduler,enable_block_reuse,use_one_model,enable_chunked_prefill",
[