mirror of
https://github.com/NVIDIA/TensorRT-LLM.git
synced 2026-02-05 02:31:33 +08:00
[None][infra] Waive failed case for release branch on 01/19 (#10795)
Signed-off-by: qqiao <qqiao@nvidia.com> Signed-off-by: Wangshanshan <30051912+dominicshanshan@users.noreply.github.com>
This commit is contained in:
parent
25bdc30162
commit
af49fbdf65
@ -386,3 +386,4 @@ perf/test_perf_sanity.py::test_e2e[disagg_upload-deepseek-r1-fp4_1k1k_ctx1_gen1_
|
||||
accuracy/test_llm_api_pytorch.py::TestLlama3_1_8BInstruct::test_bfloat16_4gpus[tp4-attn_backend=TRTLLM-torch_compile=True] SKIP (https://nvbugs/5826604)
|
||||
disaggregated/test_disaggregated.py::test_disaggregated_mixed[TinyLlama-1.1B-Chat-v1.0] SKIP (https://nvbugs/5834212)
|
||||
accuracy/test_cli_flow.py::TestLlama2_7B::test_fp8 SKIP (https://nvbugs/5819452)
|
||||
accuracy/test_llm_api_pytorch.py::TestDeepSeekV3Lite::test_bfloat16_4gpus[ep4-mtp_nextn=2-attention_dp=True-cuda_graph=True-overlap_scheduler=True-torch_compile=False] SKIP (https://nvbugs/5800646)
|
||||
|
||||
Loading…
Reference in New Issue
Block a user