nvidia_nim.e2e_request_latency.seconds.bucket
(count) | The observations of end to end request latency bucketed by seconds. |
nvidia_nim.e2e_request_latency.seconds.count
(count) | The total number of observations of end to end request latency. |
nvidia_nim.e2e_request_latency.seconds.sum
(count) | The sum of end to end request latency in seconds.
Shown as second |
nvidia_nim.generation_tokens.count
(count) | Number of generation tokens processed.
Shown as token |
nvidia_nim.gpu_cache_usage_percent
(gauge) | GPU KV-cache usage. 1 means 100 percent usage.
Shown as fraction |
nvidia_nim.num_request.max
(gauge) | The max number of concurrently running requests.
Shown as request |
nvidia_nim.num_requests.running
(gauge) | Number of requests currently running on GPU.
Shown as request |
nvidia_nim.num_requests.waiting
(gauge) | Number of requests waiting.
Shown as request |
nvidia_nim.process.cpu_seconds.count
(count) | Total user and system CPU time spent in seconds.
Shown as second |
nvidia_nim.process.max_fds
(gauge) | Maximum number of open file descriptors.
Shown as file |
nvidia_nim.process.open_fds
(gauge) | Number of open file descriptors.
Shown as file |
nvidia_nim.process.resident_memory_bytes
(gauge) | Resident memory size in bytes.
Shown as byte |
nvidia_nim.process.start_time_seconds
(gauge) | Time in seconds since process started.
Shown as second |
nvidia_nim.process.virtual_memory_bytes
(gauge) | Virtual memory size in bytes.
Shown as byte |
nvidia_nim.prompt_tokens.count
(count) | Number of prefill tokens processed.
Shown as token |
nvidia_nim.python.gc.collections.count
(count) | Number of times this generation was collected. |
nvidia_nim.python.gc.objects.collected.count
(count) | Objects collected during GC. |
nvidia_nim.python.gc.objects.uncollectable.count
(count) | Uncollectable objects found during GC. |
nvidia_nim.python.info
(gauge) | Python platform information. |
nvidia_nim.request.failure.count
(count) | The count of failed requests.
Shown as request |
nvidia_nim.request.finish.count
(count) | The count of finished requests.
Shown as request |
nvidia_nim.request.generation_tokens.bucket
(count) | Number of generation tokens processed. |
nvidia_nim.request.generation_tokens.count
(count) | Number of generation tokens processed. |
nvidia_nim.request.generation_tokens.sum
(count) | Number of generation tokens processed.
Shown as token |
nvidia_nim.request.prompt_tokens.bucket
(count) | Number of prefill tokens processed. |
nvidia_nim.request.prompt_tokens.count
(count) | Number of prefill tokens processed. |
nvidia_nim.request.prompt_tokens.sum
(count) | Number of prefill tokens processed.
Shown as token |
nvidia_nim.request.success.count
(count) | Count of successfully processed requests. |
nvidia_nim.time_per_output_token.seconds.bucket
(count) | The observations of time per output token bucketed by seconds. |
nvidia_nim.time_per_output_token.seconds.count
(count) | The total number of observations of time per output token. |
nvidia_nim.time_per_output_token.seconds.sum
(count) | The sum of time per output token in seconds.
Shown as second |
nvidia_nim.time_to_first_token.seconds.bucket
(count) | The observations of time to first token bucketed by seconds. |
nvidia_nim.time_to_first_token.seconds.count
(count) | The total number of observations of time to first token. |
nvidia_nim.time_to_first_token.seconds.sum
(count) | The sum of time to first token in seconds.
Shown as second |
