lework / llm-benchmark
LLM 并发性能测试工具,支持自动化压力测试和性能报告生成。
☆37Updated last month
Alternatives and similar repositories for llm-benchmark:
Users that are interested in llm-benchmark are comparing it to the libraries listed below
- ☆41Updated 5 months ago
- GOT的vLLM加速实现 并结合 MinerU 实现RAG中的pdf 解析☆56Updated 5 months ago
- 视觉信息抽取任务中,使用OCR识别结果规范多模态大模型的回答☆29Updated 3 months ago
- 一些大语言模型和多模态模型的应用,主要包括Rag,小模型,Agent,跨模态搜索,OCR等等☆164Updated 5 months ago
- 安卓手机部署DeepSeek-R1 蒸馏的1.5B模型☆20Updated 2 months ago
- 检测和提取各种场景图片中的表格区 域,并纠正透视和旋转问题 Detect and extract table regions from images in various scenarios, and correct perspective and rotation i…☆81Updated 4 months ago
- 通义千问VLLM推理部署DEMO☆569Updated last year
- 模型 llava-Qwen2-7B-Instruct-Chinese-CLIP 增强中文文字识别能力和表情包内涵识别能力,接近gpt4o、claude-3.5-sonnet的识别水平!☆22Updated 9 months ago
- In this fast-paced world, we all need a little something to spice up life. Whether you need a glass of sweet talk to lift your spirits or…☆52Updated 3 months ago
- LLM 推理服务性能测试☆39Updated last year
- 专注于对话系统领域的技术分享,重点写《Dify应用操作和源码剖析》专栏。☆92Updated 9 months ago
- ☆38Updated last month
- LLM101n: Let's build a Storyteller 中文版☆131Updated 8 months ago
- run ChatGLM2-6B in BM1684X☆49Updated last year
- qwen2 and llama3 cpp implementation☆44Updated 10 months ago
- ☆98Updated 2 years ago
- LLM Tokenizer with BPE algorithm☆31Updated 11 months ago
- a simple lightweight large language model pipeline framework.☆23Updated this week
- ☆90Updated last year
- unify-easy-llm(ULM)旨在打造一个简易的一键式大模型训练工具,支持Nvidia GPU、Ascend NPU等不同硬件以及常用的大模型。☆55Updated 9 months ago
- 训练一个对中文支持更好的LLaVA模型,并开源训练代码和数据。☆54Updated 7 months ago
- ☆59Updated last year
- 基于大语言模型的检索增强生成RAG示例☆144Updated 4 months ago
- 一个基于多模态大模型的图表解析器☆29Updated last month
- 研究GOT-OCR-项目落地加速,不限语言☆60Updated 6 months ago
- 大模型预训练中文语料清洗及质量评估 Large model pre-training corpus cleaning☆57Updated 9 months ago
- DeepSpeed Tutorial☆95Updated 8 months ago
- async inference for machine learning model☆26Updated 2 years ago
- vLLM Documentation in Chinese Simplified / vLLM 中文文档☆61Updated this week
- ☆48Updated this week