v2.0.0：多上下文长度测试(默认512/2048/8192/32768/131072)+测试前空转预热(不计速度)+解码输出默认128+每长度采样默认2+Excel(xlsx)导出+详情按长度分组+接口输入框图标美化+README文档

app.py

@@ -1,8 +1,9 @@
 # -*- coding: utf-8 -*-
 """LLM 速度测试台 - Flask 主应用"""
+import io
 import json
 
-from flask import Flask, jsonify, request, send_from_directory
+from flask import Flask, jsonify, request, send_file, send_from_directory
 
 import config
 import database as db
@@ -139,5 +140,150 @@ def del_test(tid):
     return jsonify({"ok": True})
 
 
+# ───────────────────────── Excel 导出 ─────────────────────────
+
+@app.route("/api/tests/<int:tid>/export.xlsx")
+def export_xlsx(tid):
+    t = db.get_test(tid)
+    if not t:
+        return jsonify({"ok": False, "error": "测试不存在"}), 404
+    t["runs"] = db.get_runs(tid)
+    t["logs"] = db.get_logs(tid)
+    try:
+        data = _build_xlsx(t)
+    except Exception as e:
+        return jsonify({"ok": False, "error": "导出失败: %s" % e}), 500
+    return send_file(data, as_attachment=True,
+                     download_name="llm_speed_test_%d.xlsx" % tid,
+                     mimetype="application/vnd.openxmlformats-officedocument.spreadsheetml.sheet")
+
+
+def _build_xlsx(t):
+    from openpyxl import Workbook
+    from openpyxl.styles import Alignment, Font, PatternFill
+
+    s = t.get("summary") or {}
+    g = t.get("gen") or {}
+    cfg = t.get("config") or {}
+    by_length = s.get("by_length") or {}
+    runs = t.get("runs") or []
+    logs = t.get("logs") or []
+
+    wb = Workbook()
+    head_fill = PatternFill("solid", fgColor="2A3550")
+    head_font = Font(color="FFFFFF", bold=True)
+    title_font = Font(bold=True, size=12)
+
+    def style_header(ws, row, ncol):
+        for c in range(1, ncol + 1):
+            cell = ws.cell(row=row, column=c)
+            cell.fill = head_fill
+            cell.font = head_font
+            cell.alignment = Alignment(horizontal="center", vertical="center")
+
+    # ── Sheet1 汇总 ──
+    ws = wb.active
+    ws.title = "汇总"
+    ws.append(["LLM 速度测试报告"])
+    ws.cell(1, 1).font = Font(bold=True, size=14)
+    info = [
+        ["测试编号", "#%d" % t["id"]],
+        ["创建时间", t.get("created_at", "")],
+        ["状态", t.get("status", "")],
+        ["提供商", t.get("provider", "")],
+        ["模型", t.get("model", "")],
+        ["Base URL", cfg.get("base_url") or "（默认）"],
+        ["上下文长度列表", " / ".join(str(x) for x in (g.get("context_lengths") or []))],
+        ["生成长度(max tokens)", g.get("max_tokens", 128)],
+        ["每个长度采样次数", g.get("samples", 2)],
+        ["预热(空转)", "开" if g.get("warmup", True) else "关"],
+        ["避免缓存", "开" if g.get("avoid_cache") else "关"],
+        ["采样(成功/总数)", "%s / %s" % (s.get("samples_ok"), s.get("samples_total"))],
+        ["校准 字符/token", s.get("calibration_chars_per_token") or "—"],
+        ["错误信息", t.get("error") or ""],
+    ]
+    for row in info:
+        ws.append(row)
+    ws.cell(14, 1).font = title_font
+    r0 = len(info) + 2
+    overall = [
+        ["平均首字延迟(ms)", s.get("avg_ttft_ms")],
+        ["最佳首字延迟(ms)", s.get("best_ttft_ms")],
+        ["平均预填充速度(tok/s)", s.get("avg_prefill_speed")],
+        ["平均解码速度(tok/s)", s.get("avg_decode_speed")],
+        ["平均提示词(tok)", s.get("avg_prompt_tokens")],
+        ["平均输出(tok)", s.get("avg_output_tokens")],
+        ["平均总耗时(ms)", s.get("avg_total_ms")],
+    ]
+    ws.cell(r0, 1, "整体平均指标").font = title_font
+    for i, row in enumerate(overall, start=r0 + 1):
+        ws.append([])
+        for j, v in enumerate(row, start=1):
+            ws.cell(row=i, column=j, value=v)
+
+    # 按上下文长度分组
+    r1 = r0 + len(overall) + 2
+    ws.cell(r1, 1, "按上下文长度分组").font = title_font
+    cols = ["上下文长度(tok)", "采样(成功/总数)", "首字ms", "预填充tok/s", "解码tok/s", "提示词tok", "输出tok", "总耗时ms"]
+    ws.append([])
+    for j, c in enumerate(cols, start=1):
+        ws.cell(row=r1 + 1, column=j, value=c)
+    style_header(ws, r1 + 1, len(cols))
+    if by_length:
+        rr = r1 + 2
+        for L in sorted(int(k) for k in by_length):
+            bl = by_length[str(L)] if str(L) in by_length else by_length[L]
+            ws.cell(row=rr, column=1, value=L)
+            ws.cell(row=rr, column=2, value="%s / %s" % (bl.get("samples_ok"), bl.get("samples_total")))
+            ws.cell(row=rr, column=3, value=bl.get("avg_ttft_ms"))
+            ws.cell(row=rr, column=4, value=bl.get("avg_prefill_speed"))
+            ws.cell(row=rr, column=5, value=bl.get("avg_decode_speed"))
+            ws.cell(row=rr, column=6, value=bl.get("avg_prompt_tokens"))
+            ws.cell(row=rr, column=7, value=bl.get("avg_output_tokens"))
+            ws.cell(row=rr, column=8, value=bl.get("avg_total_ms"))
+            rr += 1
+    else:
+        ws.cell(row=r1 + 2, column=1, value="（无成功采样数据）")
+    for col, w in zip("ABCDEFGH", [22, 20, 12, 14, 14, 12, 12, 14]):
+        ws.column_dimensions[col].width = w
+
+    # ── Sheet2 采样明细 ──
+    ws2 = wb.create_sheet("采样明细")
+    h2 = ["序号", "上下文长度tok", "提示词tok", "缓存tok", "首字ms", "预填充tok/s",
+          "输出tok", "解码tok/s", "总耗时ms", "备注"]
+    ws2.append(h2)
+    style_header(ws2, 1, len(h2))
+    for i, r in enumerate(runs, start=1):
+        m = r.get("metrics") or {}
+        ws2.append([
+            i,
+            r.get("context_length") or m.get("context_length") or "",
+            m.get("prompt_tokens") or "",
+            m.get("cached_tokens") if m.get("cached_tokens") else "",
+            m.get("ttft_ms"),
+            m.get("prefill_speed"),
+            m.get("output_tokens"),
+            m.get("decode_speed"),
+            m.get("total_ms"),
+            r.get("error") or "OK",
+        ])
+    for col, w in zip("ABCDEFGHIJ", [8, 14, 12, 10, 12, 14, 12, 14, 12, 30]):
+        ws2.column_dimensions[col].width = w
+
+    # ── Sheet3 日志 ──
+    ws3 = wb.create_sheet("日志")
+    ws3.append(["相对时间(s)", "级别", "内容"])
+    style_header(ws3, 1, 3)
+    for l in logs:
+        ws3.append([l.get("rel", 0), l.get("level", ""), l.get("msg", "")])
+    for col, w in zip("ABC", [14, 10, 90]):
+        ws3.column_dimensions[col].width = w
+
+    bio = io.BytesIO()
+    wb.save(bio)
+    bio.seek(0)
+    return bio
+
+
 if __name__ == "__main__":
     app.run(host=config.HOST, port=config.PORT, threaded=True, debug=False)