Skip to content
Merged
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
3 changes: 3 additions & 0 deletions scripts/performance/perf_plugins.py
Original file line number Diff line number Diff line change
Expand Up @@ -275,6 +275,9 @@ def _set_model_specific_environment_variables(
):
executor.env_vars["PYTORCH_CUDA_ALLOC_CONF"] = "expandable_segments:True"

if model_family_name in ["deepseek"]:
executor.env_vars["NVTE_ALLOW_NONDETERMINISTIC_ALGO"] = "0"

del_cudnn_ln = True
if gpu in ["h100"]:
if model_family_name == "llama" and model_recipe_name == "llama3_8b" and train_task == "pretrain":
Expand Down
Loading