mirror of
https://github.com/NVIDIA/TensorRT-LLM.git
synced 2026-02-04 18:21:52 +08:00
[None][infra] Waive failed cases for main on 1/28 (#11053)
Signed-off-by: qqiao <qqiao@nvidia.com>
This commit is contained in:
parent
e70a55bd94
commit
0ffa77af51
@ -364,4 +364,10 @@ test_e2e.py::test_ptp_quickstart_advanced_ngram[Llama-3.1-8B-Instruct-llama-3.1-
|
||||
accuracy/test_llm_api_pytorch.py::TestDeepSeekR1::test_fp8_blockscale[throughput_mtp] SKIP (https://nvbugs/5839028)
|
||||
unittest/kv_cache_manager_v2_tests/test_kv_cache_manager_v2.py::TestNoBatching::test_naive_0 SKIP (https://nvbugs/5841954)
|
||||
unittest/_torch/modules/test_fused_moe.py::test_fused_moe_alltoall_fp4[DeepEP] SKIP (https://nvbugs/5841976)
|
||||
unittest/_torch/modeling/test_modeling_nemotron_h.py::test_nemotron_h_cuda_graph_overlap_scheduler (https://nvbugs/5843316)
|
||||
unittest/_torch/modeling/test_modeling_nemotron_h.py::test_nemotron_h_cuda_graph_overlap_scheduler SKIP (https://nvbugs/5843316)
|
||||
examples/test_mistral.py::test_mistral_with_bf16_lora_torch[mistral-7b-v0.1] SKIP (https://nvbugs/5846178)
|
||||
accuracy/test_llm_api_pytorch.py::TestDeepSeekR1::test_fp8_blockscale[latency] SKIP (https://nvbugs/5846024)
|
||||
accuracy/test_llm_api_pytorch.py::TestDeepSeekV3Lite::test_bfloat16_4gpus[pp4-mtp_nextn=2-attention_dp=True-cuda_graph=True-overlap_scheduler=True-torch_compile=False] SKIP (https://nvbugs/5846050)
|
||||
accuracy/test_llm_api_pytorch.py::TestDeepSeekV3Lite::test_bfloat16_4gpus[pp4-mtp_nextn=2-attention_dp=True-cuda_graph=True-overlap_scheduler=True-torch_compile=True] SKIP (https://nvbugs/5846154)
|
||||
perf/test_perf_sanity.py::test_e2e[aggr_upload-deepseek_r1_fp4_v2_grace_blackwell-r1_fp4_v2_dep4_mtp1_1k8k] SKIP (https://nvbugs/5846166)
|
||||
accuracy/test_disaggregated_serving.py::TestDeepSeekV32Exp::test_auto_dtype[False] SKIP (https://nvbugs/5847284)
|
||||
|
||||
Loading…
Reference in New Issue
Block a user