NumKong

ucture.

ating such kernels easier (https://github.com/scipy/scipy/issues/21645#issuecomment-239...). For many-to-many distance calculations on low-dimensional vectors, the bottleneck is often in the reciprocal square roots. Using LibC is slow but highly accurate. Intrinsics are faster, but you'll need several Newton-Raphson iterations for precision, and the number of iterations varies between x86 and Arm architectures (https://github.com/ashvardanian/simsimd?tab=readme-ov-file#c...). When dealing with high-dimensional vectors, you start competing with BLAS implementations, though they, too, have limitations on newer hardware or in mixed precision scenarios.

ge and are stable enough. Avoiding singletons and having encapsulated context objects like `HPyContext` is definitely a great thing to have, especially in the multi-threaded Python future or in complex environments with multiple sub-interpreters. But this doesn't really solve the problem if, under the hood, the `HPyContext` still redirects to CPython's singleton. I've also looked at the linked benchmarks (<https://pypy.org/posts/2019/12/hpy-kick-off-sprint-report-18...>). They are dated from 2019, five years ago, and already mention CPython's `METH_FASTCALL` fast calling convention, but it seems like they are not compared to it. In either case, parsing arguments from one "ll" string specifier is hardly a detailed benchmark if the underlying magic isn't explained. I occasionally do one-off benchmarks as well, but it's better to describe the principle—why the thing is supposed to be faster. For example, if you're concerned about performance, you'd just parse the arguments directly from the tuple without string formatters—like this: <https://github.com/ashvardanian/SimSIMD/blob/80cc4bcaddbdee9a0c0e991e13376c234aff3…> It’s more error-prone, but it would be cool to see if a high-level solution can achieve under a 10% latency penalty. Hope this is useful :)