mirror of
https://github.com/NVIDIA/TensorRT-LLM.git
synced 2026-01-14 06:27:45 +08:00
[TRTLLM-8638][fix] Add failed cases into waives.txt (#8590)
Signed-off-by: xinhe-nv <200704525+xinhe-nv@users.noreply.github.com>
This commit is contained in:
parent
95d39e6e76
commit
59375e8bed
@ -358,8 +358,8 @@ class TestLlama3_1_8BInstruct(LlmapiAccuracyTestHarness):
|
||||
MODEL_NAME = "meta-llama/Llama-3.1-8B-Instruct"
|
||||
MODEL_PATH = f"{llm_models_root()}/llama-3.1-model/Llama-3.1-8B-Instruct"
|
||||
|
||||
@skip_pre_hopper
|
||||
@pytest.mark.skip_less_device(2)
|
||||
@pytest.mark.skip_less_device_memory(32000)
|
||||
@pytest.mark.parametrize("disable_overlap_scheduler", [False, True])
|
||||
@pytest.mark.parametrize("ctx_enable_block_reuse", [True, False])
|
||||
@pytest.mark.parametrize("gen_enable_block_reuse", [True, False])
|
||||
|
||||
@ -389,3 +389,9 @@ unittest/llmapi/test_llm_multi_gpu_pytorch.py::test_llm_rpc_tp2 SKIP (https://nv
|
||||
accuracy/test_llm_api_pytorch.py::TestQwen2_VL_7B::test_auto_dtype SKIP (https://nvbugs/5602338)
|
||||
unittest/llmapi/test_memory_profiling.py SKIP (https://nvbugs/5580781)
|
||||
test_e2e.py::test_ptp_quickstart_multimodal[qwen2.5-vl-7b-instruct-Qwen2.5-VL-7B-Instruct-image-False] SKIP (https://nvbugs/5568825)
|
||||
accuracy/test_disaggregated_serving.py::TestLlama3_1_8BInstruct::test_ctx_pp_gen_tp_asymmetric[GSM8K-gen_tp=1-ctx_pp=2] SKIP (https://nvbugs/5582277)
|
||||
accuracy/test_disaggregated_serving.py::TestLlama3_1_8BInstruct::test_ctx_pp_gen_tp_asymmetric[GSM8K-gen_tp=1-ctx_pp=4] SKIP (https://nvbugs/5582277)
|
||||
accuracy/test_disaggregated_serving.py::TestLlama3_1_8BInstruct::test_ctx_pp_gen_tp_asymmetric[GSM8K-gen_tp=2-ctx_pp=2] SKIP (https://nvbugs/5582277)
|
||||
accuracy/test_disaggregated_serving.py::TestLlama3_1_8BInstruct::test_ctx_pp_gen_tp_asymmetric[GSM8K-gen_tp=2-ctx_pp=4] SKIP (https://nvbugs/5582277)
|
||||
accuracy/test_disaggregated_serving.py::TestLlama3_1_8BInstruct::test_ctx_pp_gen_tp_asymmetric[MMLU-gen_tp=2-ctx_pp=2] SKIP (https://nvbugs/5582277)
|
||||
accuracy/test_disaggregated_serving.py::TestLlama3_1_8BInstruct::test_ctx_pp_gen_tp_asymmetric[MMLU-gen_tp=2-ctx_pp=4] SKIP (https://nvbugs/5582277)
|
||||
|
||||
Loading…
Reference in New Issue
Block a user