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

[Infra] - Waive failed tests in post-merge (#6176)

Browse Source 
Signed-off-by: qqiao <qqiao@nvidia.com>
This commit is contained in:
Emma Qiao 2025-07-18 17:34:34 +08:00 committed by GitHub
parent a95f31e72a
commit 77acb4f753
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
2 changed files with 11 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

10
tests/integration/test_lists/waives.txt
View File

@ -438,3 +438,13 @@ examples/test_multimodal.py::test_llm_multimodal_general[fuyu-8b-pp:1-tp:1-float
test_e2e.py::test_ptp_quickstart SKIP (https://nvbugs/5387762)
triton_server/test_triton_llm.py::test_llava_onevision[test_basic-False-1---False-True-False-0-128-disableDecoupleMode-inflight_fused_batching-disableTrtOverlap-0.2-max_utilization---1-1-1-False-tensorrt_llm_bls] SKIP (https://nvbugs/5396437)
triton_server/test_triton_llm.py::test_llava_onevision[test_video-False-1---False-True-False-0-128-disableDecoupleMode-inflight_fused_batching-disableTrtOverlap-0.2-guaranteed_no_evict---1-1-1-False-tensorrt_llm_bls] SKIP (https://nvbugs/5396437)
triton_server/test_triton.py::test_cpp_unit_tests[cpp-unit-tests] SKIP (https://nvbugs/5401088)
accuracy/test_llm_api_pytorch.py::TestGemma3_27BInstruct::test_auto_dtype SKIP (https://nvbugs/5401114)
test_e2e.py::test_ptp_quickstart_multimodal[gemma-3-27b-it-gemma/gemma-3-27b-it-image-True] SKIP (https://nvbugs/5401114)
accuracy/test_llm_api_pytorch.py::TestQwen3_30B_A3B::test_nvfp4[dep4_latency_moe_trtllm] SKIP (https://nvbugs/5401163)
accuracy/test_llm_api_pytorch.py::TestQwen3_30B_A3B::test_nvfp4[tep4_latency_moe_trtllm] SKIP (https://nvbugs/5401163)
examples/test_recurrentgemma.py::test_llm_recurrentgemma_1gpu[use_cpp_session-recurrentgemma-2b-use_paged_cache-int4_awq-float16-enable_attn_plugin-enable_gemm_plugin] SKIP (https://nvbugs/5401233)
triton_server/test_triton_llm.py::test_gpt_disaggregated_serving_bls[test_basic-False-1-top_k_top_p--False-True-True-0-128-enableDecoupleMode-inflight_fused_batching-disableTrtOverlap-0.2-max_utilization---1-1-1-True-tensorrt_llm_bls] SKIP (https://nvbugs/5401261)
triton_server/test_triton.py::test_gpt_disaggregated_serving_bls[gpt-disaggregated-serving-bls] SKIP (https://nvbugs/5401261)
examples/test_recurrentgemma.py::test_llm_recurrentgemma_2gpu[recurrentgemma-2b] SKIP (https://nvbugs/5401233)
examples/test_multimodal.py::test_llm_multimodal_general[VILA1.5-3b-pp:1-tp:1-float16-bs:1-cpp_e2e:False-nb:1] SKIP (https://nvbugs/5401156)

1
tests/unittest/llmapi/test_llm_pytorch.py
View File

@ -254,6 +254,7 @@ def test_llama_7b_multi_lora():
# TODO smor: currently Nemotron-Super-49B-v1 with LoRA memory consumption is overly high
# https://jirasw.nvidia.com/browse/TRTLLM-5045
@pytest.mark.skip(reason="https://nvbugs/5401210")
@skip_gpu_memory_less_than_138gb
def test_nemotron_nas_lora() -> None:
lora_config = LoraConfig(lora_dir=[