bridge.models.deepseek.deepseek_v3_bridge

Module Contents

Classes

DeepSeekV3Bridge

Megatron Bridge for DeepSeek-V3.

Data

__all__
_dequant_fp8_blockwise

API

bridge.models.deepseek.deepseek_v3_bridge.__all__

[‘DeepSeekV3Bridge’, ‘_dequant_fp8_blockwise’]

bridge.models.deepseek.deepseek_v3_bridge._dequant_fp8_blockwise

None

class bridge.models.deepseek.deepseek_v3_bridge.DeepSeekV3Bridge

Bases: megatron.bridge.models.conversion.model_bridge.MegatronModelBridge

Megatron Bridge for DeepSeek-V3.

provider_bridge(

hf_pretrained: megatron.bridge.models.hf_pretrained.causal_lm.PreTrainedCausalLM,

) → megatron.bridge.models.mla_provider.MLAModelProvider

classmethod megatron_to_hf_config(

provider: megatron.bridge.models.mla_provider.MLAModelProvider,

) → dict

mapping_registry() → megatron.bridge.models.conversion.mapping_registry.MegatronMappingRegistry

maybe_modify_loaded_hf_weight(

hf_param: Union[str, dict[str, str]],

hf_state_dict: Mapping[str, torch.Tensor],

) → Union[torch.Tensor, dict[str, torch.Tensor]]

Load HF weights and dequantize FP8 tensors on the fly.

DeepSeek-V3 ships linear weights as float8_e4m3fn with per-block scale factors stored in <key>_scale_inv (128x128 blocks). The true bf16 weight is::

w_bf16 = fp8_weight.float() * scale_inv_block

Without this override the bridge would do a bare .to(bf16) cast in ColumnParallelMapping.hf_to_megatron (param_mapping.py:905), discarding the per-block scales — the resulting model produces random-looking logits.

static _maybe_dequantize_fp8(

weight: torch.Tensor,

param_name: str,

hf_state_dict: Mapping[str, torch.Tensor],

) → torch.Tensor

Dequantize weight if it is stored as FP8 with a matching *_scale_inv.

maybe_modify_converted_hf_weight(

task: megatron.bridge.models.conversion.model_bridge.WeightConversionTask,

converted_weights_dict: Dict[str, torch.Tensor],

hf_state_dict: Mapping[str, torch.Tensor],

) → Dict[str, torch.Tensor]

Add rotary embedding inverse frequency parameter if needed.