Skip to content

Commit 1c14e0e

Browse files
authored
Update QuarantineTests for maxtext_gpu_end_to_end DAG. (#570)
* Update QuarantineTests for maxtext_gpu_end_to_end DAG. * Add a bug id in TestInfo.details. * Format the file.
1 parent a2b0882 commit 1c14e0e

File tree

1 file changed

+27
-124
lines changed

1 file changed

+27
-124
lines changed

dags/common/quarantined_tests.py

Lines changed: 27 additions & 124 deletions
Original file line numberDiff line numberDiff line change
@@ -32,147 +32,50 @@ class QuarantineTests:
3232

3333
tests = {
3434
# DAG: maxtext_gpu_end_to_end
35-
"maxtext-pinned-train-c4-data-h100-80gb-8": TestInfo(
36-
team.LLM_DEVX, "2024-11-11"
37-
),
38-
"maxtext-pinned-train-c4-data-h100-mega-80gb-8": TestInfo(
39-
team.LLM_DEVX, "2024-11-11"
40-
),
41-
"maxtext-stable-train-c4-data-h100-mega-80gb-8": TestInfo(
42-
team.LLM_DEVX, "2024-11-11"
43-
),
44-
"maxtext-pinned-train-synthetic-data-h100-80gb-8": TestInfo(
45-
team.LLM_DEVX, "2024-11-11"
46-
),
47-
"maxtext-pinned-train-synthetic-data-h100-mega-80gb-8": TestInfo(
48-
team.LLM_DEVX, "2024-11-11"
49-
),
50-
"maxtext-stable-train-synthetic-data-h100-mega-80gb-8": TestInfo(
51-
team.LLM_DEVX, "2024-11-11"
52-
),
53-
"maxtext-pinned-train-flash-h100-80gb-8": TestInfo(
54-
team.LLM_DEVX, "2024-11-11"
55-
),
56-
"maxtext-pinned-train-flash-h100-mega-80gb-8": TestInfo(
57-
team.LLM_DEVX, "2024-11-11"
58-
),
59-
"maxtext-stable-train-flash-h100-mega-80gb-8": TestInfo(
60-
team.LLM_DEVX, "2024-11-11"
61-
),
62-
"maxtext-pinned-train-quarter-batch-size-h100-80gb-8": TestInfo(
63-
team.LLM_DEVX, "2024-11-11"
64-
),
65-
"maxtext-pinned-train-quarter-batch-size-h100-mega-80gb-8": TestInfo(
66-
team.LLM_DEVX, "2024-11-11"
67-
),
68-
"maxtext-stable-train-quarter-batch-size-h100-mega-80gb-8": TestInfo(
69-
team.LLM_DEVX, "2024-11-11"
70-
),
71-
"maxtext-pinned-train-int8-h100-80gb-8": TestInfo(
72-
team.LLM_DEVX, "2024-11-11"
73-
),
74-
"maxtext-pinned-train-int8-h100-mega-80gb-8": TestInfo(
75-
team.LLM_DEVX, "2024-11-11"
76-
),
77-
"maxtext-stable-train-int8-h100-mega-80gb-8": TestInfo(
78-
team.LLM_DEVX, "2024-11-11"
79-
),
80-
"maxtext-pinned-train-fp8-h100-80gb-8": TestInfo(
81-
team.LLM_DEVX, "2024-11-11"
82-
),
83-
"maxtext-pinned-train-fp8-h100-mega-80gb-8": TestInfo(
84-
team.LLM_DEVX, "2024-11-11"
85-
),
86-
"maxtext-stable-train-fp8-h100-mega-80gb-8": TestInfo(
87-
team.LLM_DEVX, "2024-11-11"
88-
),
89-
"maxtext-pinned-decode-h100-80gb-8": TestInfo(
90-
team.LLM_DEVX, "2024-11-11"
91-
),
92-
"maxtext-pinned-decode-h100-mega-80gb-8": TestInfo(
93-
team.LLM_DEVX, "2024-11-11"
94-
),
95-
"maxtext-stable-decode-h100-mega-80gb-8": TestInfo(
96-
team.LLM_DEVX, "2024-11-11"
97-
),
98-
"maxtext-pinned-decode-quarter-batch-size-h100-80gb-8": TestInfo(
99-
team.LLM_DEVX, "2024-11-11"
100-
),
101-
"maxtext-pinned-decode-quarter-batch-size-h100-mega-80gb-8": TestInfo(
102-
team.LLM_DEVX, "2024-11-11"
103-
),
104-
"maxtext-stable-decode-quarter-batch-size-h100-mega-80gb-8": TestInfo(
105-
team.LLM_DEVX, "2024-11-11"
106-
),
107-
"maxtext-pinned-generate-param-only-checkpoint-h100-80gb-8": TestInfo(
108-
team.LLM_DEVX, "2024-11-11"
109-
),
110-
"maxtext-pinned-generate-param-only-checkpoint"
111-
"-h100-mega-80gb-8": TestInfo(team.LLM_DEVX, "2024-11-11"),
112-
"maxtext-stable-generate-param-only-checkpoint"
113-
"-h100-mega-80gb-8": TestInfo(team.LLM_DEVX, "2024-11-11"),
114-
"maxtext-pinned-generate-param-only-checkpoint"
115-
"-int8-h100-80gb-8": TestInfo(team.LLM_DEVX, "2024-11-11"),
116-
"maxtext-pinned-generate-param-only-checkpoint"
117-
"-int8-h100-mega-80gb-8": TestInfo(team.LLM_DEVX, "2024-11-11"),
118-
"maxtext-stable-generate-param-only-checkpoint"
119-
"-int8-h100-mega-80gb-8": TestInfo(team.LLM_DEVX, "2024-11-11"),
120-
"maxtext-pinned-grain-checkpoint-determinism-h100-80gb-8": TestInfo(
121-
team.LLM_DEVX, "2024-11-11"
122-
),
123-
"maxtext-pinned-grain-checkpoint-determinism-h100-mega-80gb-8": TestInfo(
124-
team.LLM_DEVX, "2024-11-11"
125-
),
126-
"maxtext-stable-grain-checkpoint-determinism-h100-mega-80gb-8": TestInfo(
127-
team.LLM_DEVX, "2024-11-11"
128-
),
12935
"maxtext-pinned-checkpoint-compatibility-h100-80gb-8": TestInfo(
130-
team.LLM_DEVX, "2024-11-11"
36+
team.LLM_DEVX,
37+
"2025-01-17",
38+
"b/390738384",
13139
),
13240
"maxtext-stable-checkpoint-compatibility-h100-80gb-8": TestInfo(
133-
team.LLM_DEVX, "2024-11-11"
41+
team.LLM_DEVX,
42+
"2025-01-17",
43+
"b/390738384",
13444
),
13545
"maxtext-pinned-checkpoint-compatibility-h100-mega-80gb-8": TestInfo(
136-
team.LLM_DEVX, "2024-11-11"
46+
team.LLM_DEVX,
47+
"2025-01-17",
48+
"b/390738384",
13749
),
13850
"maxtext-stable-checkpoint-compatibility-h100-mega-80gb-8": TestInfo(
139-
team.LLM_DEVX, "2024-11-11"
51+
team.LLM_DEVX,
52+
"2025-01-17",
53+
"b/390738384",
14054
),
14155
"maxtext-pinned-llama2-7b-train-1node-h100-80gb-8": TestInfo(
142-
team.LLM_DEVX, "2024-11-11"
143-
),
144-
"maxtext-stable-llama2-7b-train-1node-h100-80gb-8": TestInfo(
145-
team.LLM_DEVX, "2024-11-11"
146-
),
147-
"maxtext-pinned-llama2-7b-train-1node-h100-mega-80gb-8": TestInfo(
148-
team.LLM_DEVX, "2024-11-11"
149-
),
150-
"maxtext-stable-llama2-7b-train-1node-h100-mega-80gb-8": TestInfo(
151-
team.LLM_DEVX, "2024-11-11"
56+
team.LLM_DEVX,
57+
"2025-01-17",
58+
"b/390738384",
15259
),
15360
"maxtext-pinned-llama2-7b-train-2node-h100-80gb-8": TestInfo(
154-
team.LLM_DEVX, "2024-11-11"
61+
team.LLM_DEVX,
62+
"2025-01-17",
63+
"b/390738384",
15564
),
15665
"maxtext-stable-llama2-7b-train-2node-h100-80gb-8": TestInfo(
157-
team.LLM_DEVX, "2024-11-11"
158-
),
159-
"maxtext-pinned-llama2-7b-train-2node-h100-mega-80gb-8": TestInfo(
160-
team.LLM_DEVX, "2024-11-11"
66+
team.LLM_DEVX,
67+
"2025-01-17",
68+
"b/390738384",
16169
),
16270
"maxtext-stable-llama2-7b-train-2node-h100-mega-80gb-8": TestInfo(
163-
team.LLM_DEVX, "2024-11-11"
71+
team.LLM_DEVX,
72+
"2025-01-17",
73+
"b/390738384",
16474
),
16575
"maxtext-pinned-llama2-7b-h100-80gb-8": TestInfo(
166-
team.LLM_DEVX, "2024-11-11"
167-
),
168-
"maxtext-stable-llama2-7b-h100-80gb-8": TestInfo(
169-
team.LLM_DEVX, "2024-11-11"
170-
),
171-
"maxtext-pinned-llama2-7b-h100-mega-80gb-8": TestInfo(
172-
team.LLM_DEVX, "2024-11-11"
173-
),
174-
"maxtext-stable-llama2-7b-h100-mega-80gb-8": TestInfo(
175-
team.LLM_DEVX, "2024-11-11"
76+
team.LLM_DEVX,
77+
"2025-01-17",
78+
"b/390738384",
17679
),
17780
# DAG: maxtext_end_to_end
17881
"chained_tests_gemma-7b_stable": TestInfo(team.LLM_DEVX, "2024-11-12"),

0 commit comments

Comments
 (0)