mirror of
https://github.com/NVIDIA/TensorRT-LLM.git
synced 2026-02-05 02:31:33 +08:00
[None][infra] Waive failed cases for main branch on 01/21 (#10882)
Signed-off-by: qqiao <qqiao@nvidia.com>
This commit is contained in:
parent
9feebb3a27
commit
165dd360b9
@ -404,3 +404,4 @@ accuracy/test_llm_api_pytorch.py::TestDeepSeekV3Lite::test_bfloat16_4gpus[ep4-mt
|
||||
accuracy/test_llm_api_pytorch.py::TestDeepSeekV3Lite::test_nvfp4_4gpus[moe_backend=CUTLASS-mtp_nextn=2-tp2pp2-fp8kv=False-attention_dp=False-cuda_graph=False-overlap_scheduler=False-torch_compile=False] SKIP (https://nvbugs/5800672)
|
||||
perf/test_perf_sanity.py::test_e2e[aggr_upload-deepseek_r1_fp4_v2_grace_blackwell-r1_fp4_v2_tp4_mtp3_1k8k] SKIP (https://nvbugs/5819053)
|
||||
perf/test_perf_sanity.py::test_e2e[disagg_upload-deepseek-r1-fp4_1k1k_ctx1_gen1_dep8_bs768_eplb0_mtp0_ccb-UCX] SKIP (https://nvbugs/5819053)
|
||||
accuracy/test_llm_api_pytorch.py::TestLlama3_1_8BInstruct::test_bfloat16_4gpus[tp4-attn_backend=TRTLLM-torch_compile=True] SKIP (https://nvbugs/5826604)
|
||||
|
||||
Loading…
Reference in New Issue
Block a user