Commit 009be9b
committed
fix(sdk): address codex review feedback on #136
- helper: open with newline="" so CRLF/CR line endings reach the server
byte-faithful instead of being silently normalized to \n. Adds a
regression test for a Windows-authored config (b"line1\r\nline2\r\n").
- example: ship examples/sdk/default.conf so create_inference.py runs
as-is without the user having to discover and create an extra file
(matches how create_inference_vllm.py ships vllm_config.yaml).
Signed-off-by: Honglin Cao <hocao@nvidia.com>1 parent 82decf1 commit 009be9b
3 files changed
Lines changed: 21 additions & 1 deletion
| Original file line number | Diff line number | Diff line change | |
|---|---|---|---|
| |||
9 | 9 | | |
10 | 10 | | |
11 | 11 | | |
12 | | - | |
| 12 | + | |
| 13 | + | |
| 14 | + | |
13 | 15 | | |
14 | 16 | | |
| Original file line number | Diff line number | Diff line change | |
|---|---|---|---|
| |||
| 1 | + | |
| 2 | + | |
| 3 | + | |
| 4 | + | |
| 5 | + | |
| 6 | + | |
| 7 | + | |
| Original file line number | Diff line number | Diff line change | |
|---|---|---|---|
| |||
39 | 39 | | |
40 | 40 | | |
41 | 41 | | |
| 42 | + | |
| 43 | + | |
| 44 | + | |
| 45 | + | |
| 46 | + | |
| 47 | + | |
| 48 | + | |
| 49 | + | |
| 50 | + | |
| 51 | + | |
| 52 | + | |
0 commit comments