Skip to content

Commit df205a9

Browse files
committed
Add new tgi_batch_inference_tokproc_duration metric to readme
1 parent f29155e commit df205a9

File tree

1 file changed

+1
-0
lines changed

1 file changed

+1
-0
lines changed

README.md

Lines changed: 1 addition & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -143,6 +143,7 @@ They are all prefixed with `tgi_`. Descriptions will be added to the table below
143143
| `tgi_batch_inference_batch_size` | `histogram` | method = "prefill" or "next_token" | |
144144
| `tgi_batch_inference_duration` | `histogram` | method = "prefill" or "next_token", makeup | |
145145
| `tgi_batch_inference_forward_duration` | `histogram` | method = "prefill" or "next_token", makeup | |
146+
| `tgi_batch_inference_tokproc_duration` | `histogram` | method = "prefill" or "next_token", makeup | |
146147
| `tgi_batch_next_tokens` | `histogram` | | Prefill only |
147148
| `tgi_batch_current_size` | `gauge` | | |
148149
| `tgi_batch_input_tokens` | `gauge` | | |

0 commit comments

Comments
 (0)