You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
| inference_model_request_total | Counter | The counter of requests broken out for each model. |`model_name`=<model-name> <br> `target_model_name`=<target-model-name>| ALPHA |
27
27
| inference_model_request_error_total | Counter | The counter of requests errors broken out for each model. |`model_name`=<model-name> <br> `target_model_name`=<target-model-name>| ALPHA |
28
28
| inference_model_request_duration_seconds | Distribution | Distribution of response latency. |`model_name`=<model-name> <br> `target_model_name`=<target-model-name>| ALPHA |
29
-
|ntpot_seconds| Distribution | Distribution of ntpot (response latency per output token) |`model_name`=<model-name> <br> `target_model_name`=<target-model-name>| ALPHA |
29
+
|normalized_time_per_output_token_seconds| Distribution | Distribution of ntpot (response latency per output token) |`model_name`=<model-name> <br> `target_model_name`=<target-model-name>| ALPHA |
30
30
| inference_model_request_sizes | Distribution | Distribution of request size in bytes. |`model_name`=<model-name> <br> `target_model_name`=<target-model-name>| ALPHA |
31
31
| inference_model_response_sizes | Distribution | Distribution of response size in bytes. |`model_name`=<model-name> <br> `target_model_name`=<target-model-name>| ALPHA |
32
32
| inference_model_input_tokens | Distribution | Distribution of input token count. |`model_name`=<model-name> <br> `target_model_name`=<target-model-name>| ALPHA |
0 commit comments