[BUG] IVF-FLAT distance computation in FP16 can lead to infinite distances

IVF-Flat in FP16 accumulate distances in FP16, which can lead to infinite distances.
To ensure accurate distance computation, FP32 should be used for accumulation.
This can be reproduced by changing the uniform distribution we're using in test to a uniform between 0.0 and 100.0

Python example

from cuvs.neighbors import ivf_flat
import cupy as cp

a=cp.random.uniform(0,100,(1000,128)).astype(cp.float16)
b=cp.random.uniform(0,100,(20,128)).astype(cp.float16)

index = ivf_flat.build(ivf_flat.IndexParams(n_lists=20), a)
distances, neighbors = index.search(ivf_flat.SearchParams(n_probes=20), index, b, 1)

print(distances.copy_to_host())
# [inf, inf, inf, ...]

Start by reproducing the Python example with FP16 inputs and the larger uniform distribution described in the issue, using ivf_flat build and search. Inspect the existing uniform-distribution test and the IVF-Flat distance computation path; done means FP32 accumulation prevents infinite distances for this case.