kanshan/TensorRT-LLMs
1
0
Fork 0
mirror of https://github.com/NVIDIA/TensorRT-LLM.git synced 2026-01-14 06:27:45 +08:00
Code Issues Actions 1 Packages Projects Releases Wiki Activity

[https://nvbugspro.nvidia.com/bug/5270564][test] skip per-hopper for llama4 (#4211)

Browse Source 
skip per-hopper for llama4

Signed-off-by: Ivy Zhang <25222398+crazydemo@users.noreply.github.com>
This commit is contained in:
Ivy Zhang 2025-05-12 15:27:15 +08:00 committed by GitHub
parent ba13b51a58
commit ee92edf2b4
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 2 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
tests/integration/defs/accuracy/test_llm_api_pytorch.py
View File

@ -202,6 +202,7 @@ class TestLlama4MaverickInstruct(LlmapiAccuracyTestHarness):
MODEL_NAME = "meta-llama/Llama-4-Maverick-17B-128E-Instruct"
MODEL_PATH = f"{llm_models_root()}/llama4-models/Llama-4-Maverick-17B-128E-Instruct"
@skip_pre_hopper
@pytest.mark.skip_less_device(8)
@parametrize_with_ids("cuda_graph", [False, True])
@pytest.mark.parametrize("tp_size,pp_size,ep_size", [(8, 1, 1), (8, 1, 4),
@ -223,6 +224,7 @@ class TestLlama4ScoutInstruct(LlmapiAccuracyTestHarness):
MODEL_NAME = "meta-llama/Llama-4-Scout-17B-16E-Instruct"
MODEL_PATH = f"{llm_models_root()}/llama4-models/Llama-4-Scout-17B-16E-Instruct"
@skip_pre_hopper
@pytest.mark.skip_less_device(8)
@parametrize_with_ids("cuda_graph", [False, True])
@pytest.mark.parametrize("tp_size,pp_size,ep_size", [(8, 1, 1), (8, 1, 4),