mirror of
https://github.com/NVIDIA/TensorRT-LLM.git
synced 2026-01-14 06:27:45 +08:00
[None][infra] Waive failed tests for main branch (#8897)
Signed-off-by: qqiao <qqiao@nvidia.com>
This commit is contained in:
parent
9ec6a6b68f
commit
4fe47faf47
@ -385,7 +385,11 @@ accuracy/test_llm_api_pytorch.py::TestDeepSeekV32::test_nvfp4_multi_gpus[baselin
|
||||
test_e2e.py::test_ptp_quickstart_multimodal_phi4mm[phi4-multimodal-instruct-fp4-multimodals/Phi-4-multimodal-instruct-FP4-image_audio] SKIP (https://nvbugs/5630274)
|
||||
accuracy/test_llm_api_pytorch.py::TestDeepSeekV32::test_fp8_blockscale[baseline] SKIP (https://nvbugs/5630345)
|
||||
accuracy/test_llm_api_pytorch.py::TestDeepSeekV32::test_fp8_blockscale[baseline_mtp1] SKIP (https://nvbugs/5630345)
|
||||
accuracy/test_llm_api_pytorch.py::TestDeepSeekV32::test_fp8_blockscale[baseline_fp8kv] SKIP (https://nvbugs/5630345,https://nvbugs/5629887)
|
||||
accuracy/test_llm_api_pytorch.py::TestDeepSeekV32::test_fp8_blockscale[baseline_fp8kv] SKIP (https://nvbugs/5630345)
|
||||
accuracy/test_llm_api_pytorch.py::TestLlama3_1_8BInstruct::test_fp8_4gpus[tp2pp2-fp8kv=True-attn_backend=FLASHINFER-torch_compile=False] SKIP (https://nvbugs/5587393)
|
||||
accuracy/test_llm_api_pytorch.py::TestDeepSeekV32::test_nvfp4_multi_gpus[baseline_fp8kv] SKIP (https://nvbugs/5629887)
|
||||
accuracy/test_llm_api_pytorch.py::TestDeepSeekV3Lite::test_nvfp4_4gpus[moe_backend=CUTLASS-mtp_nextn=0-pp4-fp8kv=True-attention_dp=True-cuda_graph=True-overlap_scheduler=True-torch_compile=False] SKIP (https://nvbugs/5503479)
|
||||
accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_w4_4gpus[tp4-cutlass-auto] SKIP (https://nvbugs/5596343)
|
||||
test_e2e.py::test_openai_chat_harmony SKIP (https://nvbugs/5596382)
|
||||
test_e2e.py::test_ptp_quickstart_multimodal_multiturn[phi4-multimodal-instruct-fp8-multimodals/Phi-4-multimodal-instruct-FP8] SKIP (https://nvbugs/5568836)
|
||||
disaggregated/test_auto_scaling.py::test_disagg_server_restart[etcd-round_robin] SKIP (https://nvbugs/5633340)
|
||||
|
||||
Loading…
Reference in New Issue
Block a user