Function dequantize_linear_weight

src/quant_utils.py:243–256 · view source on GitHub ↗

(
    qweight: torch.Tensor,
    scale: torch.Tensor,
    zero: torch.Tensor,
    perm: Optional[torch.Tensor] = None,
)

Source from the content-addressed store, hash-verified

source not stored for this graph (policy: none)

nothing calls this directly

dequantizeFunction · 0.85

no test coverage detected