remove temp scripts

Author: Deleter-D

benchmarks/format_benchmark_metrics.py

@@ -74,7 +74,7 @@ Metrics are aligned with `benchmark_serving.py --percentile-metrics`:
 | `ttft` | Time to First Token (client arrival → first token) | ms |
 | `s_ttft` | Server TTFT (inference start → first token) | ms |
 | `tpot` | Time per Output Token (excluding first token) | ms |
-| `itl` | Inter-token Latency | ms |
+| `s_itl` | Infer Inter-token Latency | ms |
 | `e2el` | End-to-end Latency (client arrival → last token) | ms |
 | `s_e2el` | Server E2EL (inference start → last token) | ms |
 | `s_decode` | Decode speed (excluding first token) | tok/s |

benchmarks/plot_benchmark_metrics.py

@@ -74,7 +74,7 @@ python -m fastdeploy.entrypoints.openai.api_server \
 | `ttft` | 首 Token 时延（客户端到达 → 首 Token） | ms |
 | `s_ttft` | 服务端首 Token 时延（推理开始 → 首 Token） | ms |
 | `tpot` | 每 Token 输出时延（不含首 Token） | ms |
-| `itl` | Token 间时延 | ms |
+| `s_itl` | 推理 Token 间时延 | ms |
 | `e2el` | 端到端时延（客户端到达 → 最后一个 Token） | ms |
 | `s_e2el` | 服务端端到端时延（推理开始 → 最后一个 Token） | ms |
 | `s_decode` | 解码速度（不含首 Token） | tok/s |

docs/benchmark.md

@@ -1911,7 +1911,7 @@ class BenchmarkMetricsConfig:
                 ttft          - Time to First Token (client arrival → first token)
                 s_ttft        - Server TTFT (inference start → first token)
                 tpot          - Time per Output Token (excluding first token)
-                itl           - Inter-token Latency
+                s_itl         - Infer Inter-token Latency
                 e2el          - End-to-end Latency (client arrival → last token)
                 s_e2el        - Server E2EL (inference start → last token)
                 s_decode      - Decode speed (tokens/s, excluding first token)
@@ -1932,7 +1932,7 @@ class BenchmarkMetricsConfig:
         "ttft",  # Time to First Token
         "s_ttft",  # Server TTFT
         "tpot",  # Time per Output Token
-        "itl",  # Inter-token Latency
+        "s_itl",  # Infer Inter-token Latency
         "e2el",  # End-to-end Latency
         "s_e2el",  # Server E2EL
         "s_decode",  # Decode speed (tok/s)

docs/zh/benchmark.md

@@ -180,8 +180,8 @@ def _compute_rolling_stats(self) -> dict:
             result["s_ttft_ms"] = self._stats(s_ttfts, percentile_values)
         if "tpot" in selected:
             result["tpot_ms"] = self._stats(tpots, percentile_values)
-        if "itl" in selected:
-            result["itl_ms"] = self._stats(all_itls, percentile_values)
+        if "s_itl" in selected:
+            result["s_itl_ms"] = self._stats(all_itls, percentile_values)
         if "e2el" in selected:
             result["e2el_ms"] = self._stats(e2els, percentile_values)
         if "s_e2el" in selected: