Skip to content

Commit 3985435

Browse files
leofangleofang
committed
Merge branch 'main' into reduce_cudart
2 parents 7f11565 + ed884c9 commit 3985435

File tree

264 files changed

+17200
-8505
lines changed

Some content is hidden

Large Commits have some content hidden by default. Use the searchbox below for content that may be hidden.

264 files changed

+17200
-8505
lines changed

‎.bandit‎

Lines changed: 4 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,4 @@
1+
# SPDX-License-Identifier: Apache-2.0
2+
3+
[bandit]
4+
skips = B101,B311

‎.github/ISSUE_TEMPLATE/bug_report.yml‎

Lines changed: 115 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,115 @@
1+
# Copyright (c) 2024-2025, NVIDIA CORPORATION & AFFILIATES. ALL RIGHTS RESERVED.
2+
#
3+
# SPDX-License-Identifier: Apache-2.0
4+
5+
name: Bug Report
6+
description: Create a report to help us improve
7+
title: '[BUG]: '
8+
labels: ['bug']
9+
body:
10+
- type: checkboxes
11+
id: check-duplicates
12+
attributes:
13+
label: Is this a duplicate?
14+
description: Check for duplicate issues.
15+
options:
16+
- label: I confirmed there appear to be no [duplicate issues](https://github.com/NVIDIA/cuda-python/issues) for this bug and that I agree to the [Code of Conduct](CODE_OF_CONDUCT.md)
17+
required: true
18+
19+
- type: dropdown
20+
id: bug-type
21+
attributes:
22+
label: Type of Bug
23+
description: What kind of bug are you running into?
24+
multiple: false
25+
options:
26+
- Silent Failure
27+
- Runtime Error
28+
- Compile-time Error
29+
- Performance
30+
- Something else
31+
validations:
32+
required: true
33+
34+
- type: dropdown
35+
id: component
36+
attributes:
37+
label: Component
38+
description: Which cuda-python component does this apply to?
39+
multiple: false
40+
options:
41+
- cuda.bindings
42+
- cuda.core
43+
- General cuda-python
44+
- Infrastructure
45+
- Not sure
46+
validations:
47+
required: true
48+
49+
- type: textarea
50+
id: description
51+
attributes:
52+
label: Describe the bug
53+
description: A clear and concise description of what problem you are running into.
54+
placeholder: "Attempting to compile a program via `cuda.core.experimental.Program.compile` throws a `ValueError`."
55+
validations:
56+
required: true
57+
58+
- type: textarea
59+
id: reproduction
60+
attributes:
61+
label: How to Reproduce
62+
description: Steps used to reproduce the bug.
63+
placeholder: |
64+
0. Construct a `cuda.core.experimental.Program` instance
65+
1. Call the `.compile(...)` method of the instance
66+
2. The call throws a `ValueError` with the following:
67+
```
68+
ValueError: Unsupported target_type="..." (supported_target_types=('ptx', 'cubin', 'ltoir'))
69+
```
70+
validations:
71+
required: true
72+
73+
- type: textarea
74+
id: expected-behavior
75+
attributes:
76+
label: Expected behavior
77+
description: A clear and concise description of what you expected to happen.
78+
placeholder: "Using `cuda.core.experimental.Program.compile(...)` should run successfully and not throw a `ValueError`"
79+
validations:
80+
required: true
81+
82+
- type: markdown
83+
attributes:
84+
value: '# System information'
85+
86+
- type: input
87+
id: operating-system
88+
attributes:
89+
label: Operating System
90+
description:
91+
If applicable, the OS version where this bug occurs.
92+
placeholder: Ubuntu Linux 20.04
93+
validations:
94+
required: false
95+
96+
- type: textarea
97+
id: nvidia-smi-output
98+
attributes:
99+
label: nvidia-smi output
100+
description: If applicable, the output from running the `nvidia-smi` command.
101+
placeholder: |
102+
+-----------------------------------------------------------------------------+
103+
| NVIDIA-SMI 495.29.05 Driver Version: 495.29.05 CUDA Version: 11.5 |
104+
|-------------------------------+----------------------+----------------------+
105+
| GPU Name Persistence-M| Bus-Id Disp.A | Volatile Uncorr. ECC |
106+
| Fan Temp Perf Pwr:Usage/Cap| Memory-Usage | GPU-Util Compute M. |
107+
| | | MIG M. |
108+
|===============================+======================+======================|
109+
| 0 NVIDIA GeForce ... Off | 00000000:41:00.0 On | N/A |
110+
| 0% 25C P8 8W / 320W | 491MiB / 10015MiB | 0% Default |
111+
| | | N/A |
112+
+-------------------------------+----------------------+----------------------+
113+
validations:
114+
required: false
115+

‎.github/ISSUE_TEMPLATE/config.yml‎

Lines changed: 4 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -1,3 +1,7 @@
1+
# Copyright (c) 2024-2025, NVIDIA CORPORATION & AFFILIATES. ALL RIGHTS RESERVED.
2+
#
3+
# SPDX-License-Identifier: Apache-2.0
4+
15
blank_issues_enabled: true
26
contact_links:
37
- name: Questions

‎.github/ISSUE_TEMPLATE/doc_request.yml‎

Lines changed: 44 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,44 @@
1+
# Copyright (c) 2024-2025, NVIDIA CORPORATION & AFFILIATES. ALL RIGHTS RESERVED.
2+
#
3+
# SPDX-License-Identifier: Apache-2.0
4+
5+
name: Documentation Request
6+
description: Suggest an idea to improve cuda-python
7+
title: '[DOC]: '
8+
labels: ['doc']
9+
10+
body:
11+
- type: checkboxes
12+
id: check-duplicates
13+
attributes:
14+
label: Is this a duplicate?
15+
description: Check for duplicate issues.
16+
options:
17+
- label: I confirmed there appear to be no [duplicate issues](https://github.com/NVIDIA/cuda-python/issues) for this bug and that I agree to the [Code of Conduct](CODE_OF_CONDUCT.md)
18+
required: true
19+
20+
- type: dropdown
21+
id: new_or_correction
22+
attributes:
23+
label: Is this for new documentation, or an update to existing docs?
24+
options:
25+
- New
26+
- Update
27+
validations:
28+
required: true
29+
30+
- type: textarea
31+
id: problem
32+
attributes:
33+
label: Describe the incorrect/future/missing documentation
34+
placeholder: "Example: A code snippet mentions function foo(args) but I cannot find any documentation on it."
35+
validations:
36+
required: true
37+
38+
- type: textarea
39+
id: search_locs
40+
attributes:
41+
label: If this is a correction, please provide a link to the incorrect documentation. If this is a new documentation request, please link to where you have looked.
42+
placeholder: |
43+
https://nvidia.github.io/cuda-python/latest/
44+

‎.github/ISSUE_TEMPLATE/feature_request.yml‎

Lines changed: 70 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,70 @@
1+
# Copyright (c) 2024-2025, NVIDIA CORPORATION & AFFILIATES. ALL RIGHTS RESERVED.
2+
#
3+
# SPDX-License-Identifier: Apache-2.0
4+
5+
name: Feature Request
6+
description: Suggest an idea to improve cuda-python
7+
title: '[FEA]: '
8+
labels: ['feature request']
9+
body:
10+
- type: checkboxes
11+
id: check-duplicates
12+
attributes:
13+
label: Is this a duplicate?
14+
description: Check for duplicate issues.
15+
options:
16+
- label: I confirmed there appear to be no [duplicate issues](https://github.com/NVIDIA/cuda-python/issues) for this request and that I agree to the [Code of Conduct](CODE_OF_CONDUCT.md)
17+
18+
- type: dropdown
19+
id: area
20+
attributes:
21+
label: Area
22+
description: What area does this request apply to?
23+
multiple: false
24+
options:
25+
- cuda.bindings
26+
- cuda.core
27+
- General cuda-python
28+
- Infrastructure
29+
- Not sure
30+
validations:
31+
required: true
32+
33+
- type: textarea
34+
id: description
35+
attributes:
36+
label: Is your feature request related to a problem? Please describe.
37+
description: A clear and concise description of what the problem is, e.g., "I would like to be able to..."
38+
placeholder: I would like to be able to use the equivalent of `cuda.core.experimental.Program.compile(...)` to compile my code to PTX.
39+
validations:
40+
required: true
41+
42+
- type: textarea
43+
id: proposed-solution
44+
attributes:
45+
label: Describe the solution you'd like
46+
description: A clear and concise description of what you want to happen.
47+
placeholder: |
48+
Support a `ptx` target_type in the `cuda.core.experimental.Program.compile(...)` function.
49+
validations:
50+
required: true
51+
52+
- type: textarea
53+
id: alternatives
54+
attributes:
55+
label: Describe alternatives you've considered
56+
description:
57+
If applicable, please add a clear and concise description of any alternative solutions or features you've
58+
considered.
59+
placeholder: The alternatives to using `cuda.core.experimental.Program.compile(...)` are unappealing. They usually involve using lower level bindings to something like nvRTC or invoking the nvcc executable.
60+
validations:
61+
required: false
62+
63+
- type: textarea
64+
id: additional-context
65+
attributes:
66+
label: Additional context
67+
description: Add any other context about the request here.
68+
placeholder: This would be helpful to have a more productive development cycle in working at the intersection of CUDA and Python for my project.
69+
validations:
70+
required: false

‎.github/ISSUE_TEMPLATE/release_checklist.yml‎

Lines changed: 4 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -1,3 +1,7 @@
1+
# Copyright (c) 2024-2025, NVIDIA CORPORATION & AFFILIATES. ALL RIGHTS RESERVED.
2+
#
3+
# SPDX-License-Identifier: Apache-2.0
4+
15
name: Release Checklist
26
description: Public checklist for release managers making a subpackage release
37
labels: ["P0"]

‎.github/PULL_REQUEST_TEMPLATE.md‎

Lines changed: 14 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,14 @@
1+
## Description
2+
3+
<!-- Every PR should have a corresponding issue that describes and motivates the work done in the PR -->
4+
closes <!-- Link issue here -->
5+
6+
<!-- Provide a standalone description of changes in this PR. -->
7+
8+
<!-- Note: The pull request title will be included in the CHANGELOG. -->
9+
10+
## Checklist
11+
<!-- TODO: - [ ] I am familiar with the [Contributing Guidelines](). -->
12+
- [ ] New or existing tests cover these changes.
13+
- [ ] The documentation is up to date with these changes.
14+

‎.github/actions/doc_preview/action.yml‎

Lines changed: 8 additions & 4 deletions
Original file line numberDiff line numberDiff line change
@@ -1,3 +1,7 @@
1+
# Copyright (c) 2024-2025, NVIDIA CORPORATION & AFFILIATES. ALL RIGHTS RESERVED.
2+
#
3+
# SPDX-License-Identifier: Apache-2.0
4+
15
name: Preview or clean up docs built from PRs
26

37
# A re-implementation based on the logic of https://github.com/rossjrw/pr-preview-action/blob/41a957c44a456a34718e9bcf825363194db5e6d5/README.md, due to limitations illustrated in NVIDIA/cuda-python#380.
@@ -17,7 +21,7 @@ runs:
1721
# Note: the PR previews will be removed once merged to main (see below)
1822
- name: Deploy doc preview
1923
if: ${{ github.ref_name != 'main' }}
20-
uses: JamesIves/github-pages-deploy-action@v4
24+
uses: JamesIves/github-pages-deploy-action@6c2d9db40f9296374acc17b90404b6e8864128c8 # v4.7.3
2125
with:
2226
git-config-name: cuda-python-bot
2327
git-config-email: [email protected]
@@ -27,7 +31,7 @@ runs:
2731

2832
- name: Leave a comment after deployment
2933
if: ${{ github.ref_name != 'main' }}
30-
uses: marocchino/sticky-pull-request-comment@v2
34+
uses: marocchino/sticky-pull-request-comment@67d0dec7b07ed060a405f9b2a64b8ab319fdd7db # v2.9.2
3135
with:
3236
header: pr-preview
3337
number: ${{ inputs.pr-number }}
@@ -43,7 +47,7 @@ runs:
4347
# The steps below are executed only when building on main.
4448
- name: Remove doc preview
4549
if: ${{ github.ref_name == 'main' }}
46-
uses: JamesIves/github-pages-deploy-action@v4
50+
uses: JamesIves/github-pages-deploy-action@6c2d9db40f9296374acc17b90404b6e8864128c8 # v4.7.3
4751
with:
4852
git-config-name: cuda-python-bot
4953
git-config-email: [email protected]
@@ -53,7 +57,7 @@ runs:
5357

5458
- name: Leave a comment after removal
5559
if: ${{ github.ref_name == 'main' }}
56-
uses: marocchino/sticky-pull-request-comment@v2
60+
uses: marocchino/sticky-pull-request-comment@67d0dec7b07ed060a405f9b2a64b8ab319fdd7db # v2.9.2
5761
with:
5862
header: pr-preview
5963
number: ${{ inputs.pr-number }}

0 commit comments

Comments
 (0)