Repository navigation
Commit b4b0b80
authored
test(serve): run the recommender integ tests on ml.g6 and ml.g7 instances (#6557)
test_recommendation_workflow_end_to_end's recommendation job, and the
endpoint the test deploys from its top recommendation, now use
ml.g7.2xlarge instead of ml.g5.2xlarge.
The JumpStart model, which the benchmark test deploys and the
recommendation test builds, now uses ml.g6.2xlarge: JumpStart has no
ml.g7 image configuration for it, and ml.g6.2xlarge gets the same
serving image as ml.g5.2xlarge.1 parent e8edd7e commit b4b0b80
1 file changed
Lines changed: 9 additions & 4 deletions
| Original file line number | Diff line number | Diff line change | |
|---|---|---|---|
| |||
43 | 43 | | |
44 | 44 | | |
45 | 45 | | |
46 | | - | |
| 46 | + | |
| 47 | + | |
47 | 48 | | |
48 | 49 | | |
49 | 50 | | |
| |||
63 | 64 | | |
64 | 65 | | |
65 | 66 | | |
66 | | - | |
| 67 | + | |
67 | 68 | | |
68 | 69 | | |
69 | 70 | | |
| |||
152 | 153 | | |
153 | 154 | | |
154 | 155 | | |
155 | | - | |
| 156 | + | |
156 | 157 | | |
157 | 158 | | |
158 | 159 | | |
| |||
197 | 198 | | |
198 | 199 | | |
199 | 200 | | |
| 201 | + | |
200 | 202 | | |
201 | 203 | | |
202 | 204 | | |
203 | | - | |
| 205 | + | |
| 206 | + | |
| 207 | + | |
| 208 | + | |
204 | 209 | | |
205 | 210 | | |
206 | 211 | | |
| |||
0 commit comments