hub / github.com/Aveiro-Lin/GraphiContact / quantize_fp4

Function quantize_fp4

src/bitsandbytes/bitsandbytes/functional.py:1102–1110 · view source on GitHub ↗

(
    A: Tensor,
    absmax: Optional[torch.Tensor] = None,
    out: Optional[torch.Tensor] = None,
    blocksize=64,
    compress_statistics=False,
    quant_storage=torch.uint8,
)

Source from the content-addressed store, hash-verified

source not stored for this graph (policy: none)

Callers

nothing calls this directly

Calls 1

quantize_4bitFunction · 0.85

Tested by

no test coverage detected