MCPcopy
hub / github.com/NVIDIA/TensorRT-LLM / WeightsLoadingConfig

Class WeightsLoadingConfig

tensorrt_llm/_torch/modules/linear.py:45–47  ·  view source on GitHub ↗

Source from the content-addressed store, hash-verified

43
44@dataclass(kw_only=True)
45class WeightsLoadingConfig:
46 weight_mode: WeightMode = WeightMode.VANILLA
47 ignore_tensor_parallel: bool = False
48
49
50class TensorParallelMode(str, enum.Enum):

Callers 7

__init__Method · 0.85
__init__Method · 0.85
__init__Method · 0.85
__init__Method · 0.85
__init__Method · 0.85
__init__Method · 0.85
__init__Method · 0.85

Calls

no outgoing calls

Tested by

no test coverage detected