TensorRT-LLMs/tensorrt_llm/metrics/enums.py
Ye Zhang bcf5ec0c9a
[None][feat] Core Metrics Implementation (#5785)
Signed-off-by: Ye Zhang <zhysishu@gmail.com>
Signed-off-by: Shunkang <182541032+Shunkangz@users.noreply.github.co>
2025-08-09 02:48:53 -04:00

16 lines
377 B
Python

from enum import Enum
class MetricNames(Enum):
TTFT = "ttft"
TPOT = "tpot"
E2E = "e2e"
REQUEST_QUEUE_TIME = "request_queue_time"
class RequestEventTiming(Enum):
ARRIVAL_TIME = "arrival_time"
FIRST_TOKEN_TIME = "first_token_time" # nosec: B105
FIRST_SCHEDULED_TIME = "first_scheduled_time"
LAST_TOKEN_TIME = "last_token_time" # nosec: B105