Skip to content
Open
Show file tree
Hide file tree
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
Original file line number Diff line number Diff line change
Expand Up @@ -30,6 +30,8 @@ def set_nemotron_3_nano_common_configs(cfg: ConfigContainer) -> None:
cfg.mixed_precision.grad_reduce_in_fp32 = False
cfg.ddp.grad_reduce_in_fp32 = False

cfg.model.moe_router_force_load_balancing = True


def nemotron_3_nano_pretrain_config_gb300(
precision: str = "bf16", mock: bool = True, config_variant: str = "v1"
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -41,6 +41,9 @@
NEMOTRON_3_NANO_PRETRAIN_CONFIG_GB300_BF16_V1 = replace(
BASE_NEMOTRON_3_NANO_CONFIG,
tensor_model_parallel_size=1,
micro_batch_size=4,
cuda_graph_impl="transformer_engine",
cuda_graph_scope=["attn", "moe_router", "moe_preprocess", "mamba"],
)
NEMOTRON_3_NANO_PRETRAIN_CONFIG_GB300_FP8_MX_V1 = NEMOTRON_3_NANO_PRETRAIN_CONFIG_GB300_BF16_V1
NEMOTRON_3_NANO_PRETRAIN_CONFIG_GB300_NVFP4_V1 = NEMOTRON_3_NANO_PRETRAIN_CONFIG_GB300_BF16_V1
Expand Down
Loading