Repository navigation
Commit 9a3b331
authored
test(serve): SD/KT-IC integ must use g6.2xlarge, not g4dn (T4) (#6141)
The LMI/vLLM JumpStart container (CUDA 12.x) does not start on ml.g4dn.xlarge
(T4/Turing): the Inference Component fails with CannotStartContainerError. Switch
INSTANCE_TYPE to ml.g6.2xlarge (L4), the smallest instance on which it starts.
Verified live: the deploy() IC path reaches InService on g6.2xlarge with both
base_model + draft_model AdditionalModelDataSources intact.1 parent c4f9b5b commit 9a3b331
1 file changed
Lines changed: 3 additions & 3 deletions
| Original file line number | Diff line number | Diff line change | |
|---|---|---|---|
| |||
30 | 30 | | |
31 | 31 | | |
32 | 32 | | |
33 | | - | |
34 | | - | |
| 33 | + | |
| 34 | + | |
35 | 35 | | |
36 | | - | |
| 36 | + | |
37 | 37 | | |
38 | 38 | | |
39 | 39 | | |
| |||
0 commit comments