MCPcopy Create free account
hub / github.com/Aveiro-Lin/GraphiContact / estimate_quantiles

Function estimate_quantiles

src/bitsandbytes/bitsandbytes/functional.py:559–622  ·  view source on GitHub ↗

Estimates 256 equidistant quantiles on the input tensor eCDF. Uses SRAM-Quantiles algorithm to quickly estimate 256 equidistant quantiles via the eCDF of the input tensor `A`. This is a fast but approximate algorithm and the extreme quantiles close to 0 and 1 have high variance / l

(
    A: Tensor,
    out: Optional[torch.Tensor] = None,
    offset: float = 1 / 512,
    num_quantiles=256,
)

Source from the content-addressed store, hash-verified

source not stored for this graph (policy: none)

Callers 1

create_quantile_mapFunction · 0.85

Calls 5

is_on_gpuFunction · 0.85
pre_callFunction · 0.85
get_ptrFunction · 0.85
post_callFunction · 0.85
toMethod · 0.45

Tested by

no test coverage detected