A high-throughput and memory-efficient inference and serving engine for LLMs
Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git
Synced Nov 15, 08:30 UTC
[GH] Add issue template for reporting CI failures (#18696)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
Cyrus Leung committed
May 26, 2025 at 15:42 UTC
4b7740a1055d2aa13b81c63f636a972024fdcd85
2 files changed
+72
-3
.github/ISSUE_TEMPLATE/400-bug-report.yml
+3
-3
@@ -81,14 +81,14 @@ body:
81
required: true
82
- type: markdown
83
attributes:
84
- value: >
85
- ⚠️ Please separate bugs of `transformers` implementation or usage from bugs of `vllm`. If you think anything is wrong with the models' output:
84
+ value: |
85
+ ⚠️ Please separate bugs of `transformers` implementation or usage from bugs of `vllm`. If you think anything is wrong with the model's output:
86
87
- Try the counterpart of `transformers` first. If the error appears, please go to [their issues](https://github.com/huggingface/transformers/issues?q=is%3Aissue+is%3Aopen+sort%3Aupdated-desc).
88
89
- If the error only appears in vllm, please provide the detailed script of how you run `transformers` and `vllm`, also highlight the difference and what you expect.
90
91
- Thanks for contributing 🎉!
91
+ Thanks for reporting 🙏!
92
- type: checkboxes
93
id: askllm
94
attributes:
.github/ISSUE_TEMPLATE/450-ci-failure.yml
new
+69
@@ -0,0 +1,69 @@
1
+name: 🧪 CI failure report
2
+description: Report a failing test.
3
+title: "[CI Failure]: "
4
+labels: ["ci-failure"]
5
+
6
+body:
7
+- type: markdown
8
+ attributes:
9
+ value: >
10
+ #### Include the name of the failing Buildkite step and test file in the title.
11
+- type: input
12
+ attributes:
13
+ label: Name of failing test
14
+ description: |
15
+ Paste in the fully-qualified name of the failing test from the logs.
16
+ placeholder: |
17
+ `path/to/test_file.py::test_name[params]`
18
+ validations:
19
+ required: true
20
+- type: checkboxes
21
+ attributes:
22
+ label: Basic information
23
+ description: Select all items that apply to the failing test.
24
+ options:
25
+ - label: Flaky test
26
+ - label: Can reproduce locally
27
+ - label: Caused by external libraries (e.g. bug in `transformers`)
28
+- type: textarea
29
+ attributes:
30
+ label: 🧪 Describe the failing test
31
+ description: |
32
+ Please provide a clear and concise description of the failing test.
33
+ placeholder: |
34
+ A clear and concise description of the failing test.
35
+
36
+ ```
37
+ The error message you got, with the full traceback and the error logs with [dump_input.py:##] if present.
38
+ ```
39
+ validations:
40
+ required: true
41
+- type: input
42
+ attributes:
43
+ label: 📝 History of failing test
44
+ description: |
45
+ Since when did the test start to fail?
46
+ You can look up its history via [Buildkite Test Suites](https://buildkite.com/organizations/vllm/analytics/suites/ci-1/tests?branch=main).
47
+
48
+ If you have time, identify the PR that caused the test to fail on main. You can do so via the following methods:
49
+
50
+ - Use Buildkite Test Suites to find the PR where the test failure first occurred, and reproduce the failure locally.
51
+
52
+ - Run [`git bisect`](https://git-scm.com/docs/git-bisect) locally.
53
+
54
+ - Manually unblock Buildkite steps for suspected PRs on main and check the results. (authorized users only)
55
+ placeholder: |
56
+ Approximate timeline and/or problematic PRs
57
+
58
+ A link to the Buildkite analytics of the failing test (if available)
59
+ validations:
60
+ required: true
61
+- type: textarea
62
+ attributes:
63
+ label: CC List.
64
+ description: >
65
+ The list of people you want to CC. Usually, this includes those who worked on the PR that failed the test.
66
+- type: markdown
67
+ attributes:
68
+ value: >
69
+ Thanks for reporting 🙏!