Fix reasoning metrics and add TPOT to bench_multiturn (#35443)

2026-09-02 11:28:47 +08:00
parent 0157f1f552
commit 2d9c64394f
4 changed files with 179 additions and 4 deletions
@@ -101,6 +101,7 @@ class RequestFuncOutput:
    success: bool = False
    latency: float = 0.0
    ttft: float = 0.0  # Time to first token
+    tpot: Optional[float] = None  # Time per output token
    itl: List[float] = field(default_factory=list)  # List of inter-token latencies
    text_chunks: List[str] = field(default_factory=list)
    prompt_len: int = 0