Skip to content

Commit f248847

Browse files
authored
Merge branch 'main' into dev
2 parents f342ef9 + fd2f5ff commit f248847

File tree

3 files changed

+20
-1
lines changed

3 files changed

+20
-1
lines changed

README.md

Lines changed: 9 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -34,6 +34,15 @@ LMeterX is a professional large language model performance testing platform that
3434
- **Web Console** - One-stop management for task creation, stopping, status tracking, and full-chain log monitoring
3535
- **Enterprise-level Deployment** - Docker containerization with elastic scaling and distributed deployment support
3636

37+
### Feature Comparison
38+
| Dimension | LMeterX | EvalScope | llmperf |
39+
|----------------------|-------------------------------------------------------------------------|---------------------------------------------------------------------------|----------------------------------------------------------|
40+
| Usage | Web UI for full-lifecycle task creation, monitoring & stop (load-test) | CLI for ModelScope ecosystem (eval & load-test) | CLI, Ray-based (load-test) |
41+
| Concurrency & Stress | Multi-process / multi-task, enterprise-scale load testing | Command-line concurrency (`--parallel`, `--rate`) | Command-line concurrency |
42+
| Test Report | Multi-model / multi-version comparison, AI analysis, visual dashboard | Basic report + visual charts (requires gradio, plotly, etc.) | Simple report |
43+
| Model & Data Support | OpenAI-compatible, custom data & model interfaces | OpenAI-compatible by default; extending APIs needs custom code | OpenAI-compatible |
44+
| Deployment & Scaling | Docker / K8s ready, easy horizontal scaling | `pip` install or source code | Source code only |
45+
3746
## 🏗️ System Architecture
3847

3948
LMeterX adopts a microservices architecture design, consisting of four core components:

README_CN.md

Lines changed: 10 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -35,6 +35,16 @@ LMeterX 是一个专业的大语言模型性能测试平台,支持基于大模
3535
- **Web控制台** - 提供任务创建、停止、状态跟踪、全链路日志监控等一站式管理
3636
- **企业级部署** - Docker容器化,支持弹性扩展与分布式部署
3737

38+
### 工具对比
39+
40+
| 维度 | LMeterX | EvalScope | llmperf |
41+
|------|---------|---------|-----------|
42+
| 使用 | 提供 Web UI:任务创建、监控、停止全生命周期管理(压测) | CLI 命令行,面向 ModelScope 生态(效果评测和压测)| CLI 命令行,依赖 Ray 框架(压测) |
43+
| 并发与压测 | 支持多进程、多任务并发,企业级规模化压测 | 支持命令参数并发 | 支持命令参数并发 |
44+
| 测试报告 | 支持多模型/多版本对比,AI 分析,提供可视化页面 | 基础报告 + 可视化图表(需额外安装 gradio, plotly等) | 简易报告 |
45+
| 模型与数据支持 | 支持 OpenAI 格式,支持自定义数据和模型接口 | 默认支持 OpenAI 格式,扩展新 API 需自行实现代码 | 支持 OpenAI 格式 |
46+
| 部署与扩展 | 提供 Docker / K8s 部署方案,易于弹性伸缩 | `pip` 或源码 | 源码 |
47+
3848
## 🏗️ 系统架构
3949

4050
LMeterX 采用微服务架构,由四个核心组件构成:

frontend/public/locales/en/translation.json

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -408,7 +408,7 @@
408408
"promptFieldPath": "Prompt",
409409
"promptFieldPathTooltip": "The key in your request payload that contains the user prompt (needed for performance metrics calculation)",
410410
"streamingResponseConfiguration": "Response Field Mapping",
411-
"streamLinePrefix": "Stream Line Prefix",
411+
"streamLinePrefix": "Data Line Prefix",
412412
"streamLinePrefixTooltip": "Text that appears at the beginning of each data line (e.g., \"data:\", \"event:\")",
413413
"dataFormatTooltip": "Format of the streaming data after removing the prefix",
414414
"jsonFormat": "JSON Format",

0 commit comments

Comments
 (0)