NVIDIA / NVIDIA/cudf

Reuse prefetched parquet metadata for decimal predicate pushdown

Open
#22,940 0 comments 0 reactions 1 assignee Claimed by @Matt711 View on GitHub
feature request libcudf pylibcudf
Dominant language
C++
Stars
9.8k
Forks
1.1k
Avg merge
3d 6m
Merged PRs (30d)
278

Description

We have the schema in C++ https://github.com/rapidsai/cudf/blob/bc6d10cb927cc0f804834c53790faf56f055faeb/cpp/include/cudf/io/parquet_schema.hpp#L869. The issue is that we need python bindings. And a small utility to convert `std::vector` to parquet schema. The logic I added in https://github.com/rapidsai/cudf/pull/21458 can probably be hoisted into said utility.

_Originally posted by @Matt711 in https://github.com/rapidsai/cudf/pull/22700#discussion_r3375319611_

Contributor guide

Open the contributing guide

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.