kanshan/TensorRT-LLMs
1
0
Fork 0
mirror of https://github.com/NVIDIA/TensorRT-LLM.git synced 2026-02-03 17:52:19 +08:00
Code Issues Actions 1 Packages Projects Releases Wiki Activity

waive

Browse Source 
Signed-off-by: Xiwen Yu <13230610+VALLIS-NERIA@users.noreply.github.com>
This commit is contained in:
Xiwen Yu 2025-09-08 21:02:35 +08:00
parent fdaf4e2985
commit e30e0c8693
1 changed files with 6 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

11
tests/unittest/_torch/auto_deploy/unit/singlegpu/test_ad_build_small_single.py
View File

@ -64,11 +64,12 @@ def _check_ad_config(experiment_config: ExperimentConfig, llm_args: LlmArgs):
attn_backend="triton",
compile_backend="torch-simple",
),
get_small_model_config(
"meta-llama/Llama-4-Scout-17B-16E-Instruct",
attn_backend="flashinfer",
compile_backend="torch-simple",
),
# disabled due to https://nvbugspro.nvidia.com/bug/5505835
# get_small_model_config(
# "meta-llama/Llama-4-Scout-17B-16E-Instruct",
# attn_backend="flashinfer",
# compile_backend="torch-simple",
# ),
get_small_model_config(
"deepseek-ai/DeepSeek-V3",
attn_backend="triton",