mirror of
https://github.com/NVIDIA/TensorRT-LLM.git
synced 2026-02-16 15:55:08 +08:00
[https://nvbugs/5837275][fix] Unwaive the failing case that cannot be… (#11137)
Signed-off-by: Jin Li <59594262+liji-nv@users.noreply.github.com>
This commit is contained in:
parent
ada463d15d
commit
9091a193a8
@ -318,10 +318,8 @@ 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)
|
||||
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_llm_api_pytorch.py::TestGLM4_5Air::test_nvfp4_multi_gpus[throughput_trtllm] SKIP (https://nvbugs/5837275)
|
||||
accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_w4_4gpus[v1_kv_cache-ep4-trtllm-fp8] SKIP (https://nvbugs/5640697)
|
||||
accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_w4_4gpus[v2_kv_cache-ep4-trtllm-fp8] SKIP (https://nvbugs/5640697)
|
||||
accuracy/test_llm_api_pytorch.py::TestGLM4_5Air::test_nvfp4_multi_gpus[throughput] SKIP (https://nvbugs/5837275)
|
||||
test_e2e.py::test_ptp_quickstart_advanced_deepseek_r1_w4afp8_8gpus[DeepSeek-R1-W4AFP8-DeepSeek-R1/DeepSeek-R1-W4AFP8] SKIP (https://nvbugs/5836830)
|
||||
accuracy/test_llm_api_pytorch.py::TestNemotronV3Super::test_auto_dtype_4gpus[4-4-True-False-False] SKIP (https://nvbugs/5823587)
|
||||
accuracy/test_llm_api_pytorch.py::TestNemotronV3Super::test_auto_dtype_4gpus[4-4-True-False-True] SKIP (https://nvbugs/5823587)
|
||||
|
||||
Loading…
Reference in New Issue
Block a user