libkvikio-cu12 24.8.2__tar.gz
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- PKG-INFO +40 -0
- pyproject.toml +6 -0
PKG-INFO
ADDED
|
@@ -0,0 +1,40 @@
|
|
|
1
|
+
Metadata-Version: 2.1
|
|
2
|
+
Name: libkvikio-cu12
|
|
3
|
+
Version: 24.8.2
|
|
4
|
+
Summary: KvikIO - GPUDirect Storage (C++)
|
|
5
|
+
Author: NVIDIA Corporation
|
|
6
|
+
License: Apache 2.0
|
|
7
|
+
Classifier: Intended Audience :: Developers
|
|
8
|
+
Classifier: Topic :: Database
|
|
9
|
+
Classifier: Topic :: Scientific/Engineering
|
|
10
|
+
Classifier: License :: OSI Approved :: Apache Software License
|
|
11
|
+
Classifier: Programming Language :: Python
|
|
12
|
+
Classifier: Programming Language :: Python :: 3.9
|
|
13
|
+
Classifier: Programming Language :: Python :: 3.10
|
|
14
|
+
Classifier: Programming Language :: Python :: 3.11
|
|
15
|
+
Project-URL: Homepage, https://github.com/rapidsai/kvikio
|
|
16
|
+
Description-Content-Type: text/markdown
|
|
17
|
+
|
|
18
|
+
# KvikIO: High Performance File IO
|
|
19
|
+
|
|
20
|
+
## Summary
|
|
21
|
+
|
|
22
|
+
KvikIO is a Python and C++ library for high performance file IO. It provides C++ and Python
|
|
23
|
+
bindings to [cuFile](https://docs.nvidia.com/gpudirect-storage/api-reference-guide/index.html),
|
|
24
|
+
which enables [GPUDirect Storage (GDS)](https://developer.nvidia.com/blog/gpudirect-storage/).
|
|
25
|
+
KvikIO also works efficiently when GDS isn't available and can read/write both host and device data seamlessly.
|
|
26
|
+
The C++ library is header-only making it easy to include in [existing projects](https://github.com/rapidsai/kvikio/blob/HEAD/cpp/examples/downstream/).
|
|
27
|
+
|
|
28
|
+
|
|
29
|
+
### Features
|
|
30
|
+
|
|
31
|
+
* Object oriented API of [cuFile](https://docs.nvidia.com/gpudirect-storage/api-reference-guide/index.html) with C++/Python exception handling.
|
|
32
|
+
* A Python [Zarr](https://zarr.readthedocs.io/en/stable/) backend for reading and writing GPU data to file seamlessly.
|
|
33
|
+
* Concurrent reads and writes using an internal thread pool.
|
|
34
|
+
* Non-blocking API.
|
|
35
|
+
* Handle both host and device IO seamlessly.
|
|
36
|
+
* Provides Python bindings to [nvCOMP](https://github.com/NVIDIA/nvcomp).
|
|
37
|
+
|
|
38
|
+
### Documentation
|
|
39
|
+
* Python: <https://docs.rapids.ai/api/kvikio/nightly/>
|
|
40
|
+
* C++: <https://docs.rapids.ai/api/libkvikio/nightly/>
|