SirlyDreamer

Docker镜像问题请到 https://github.com/SirlyDreamer/Yunzai-Bot 下开issue反馈，不要给乐佬添麻烦了(～￣▽￣)～

您的代码： ```cpp LL BSGS(LL a, LL b, LL p) { // a^x = b (mod p) a %= p; if (!a && !b) return 1; if (!a) return -1; static...

请求支持 Huggingface TGI 推理框架 API

1

**例行检查** [//]: # (方框内删除已有的空格，填 x 号) + [x] 我已确认目前没有类似 issue + [x] 我已确认我已升级到最新版本 + [x] 我已完整查看过项目 README，已确定现有版本无法满足需求 + [x] 我理解并愿意跟进此 issue，协助测试和提供反馈 + [x] 我理解并认可上述内容，并理解项目维护者精力有限，**不遵循规则的 issue 可能会被无视或直接关闭** **功能描述** 添加对 [HuggingFace TGI](https://github.com/huggingface/text-generation-inference.git)...

[Bug] Setting `max_tokens` didn't work when using OpenAI models.

1

### Bug Description The payload of request didn't contains 'max_tokens'. ### Steps to Reproduce 1. Go to 'settings', and set max_tokens to any value. 2. Open Chrome Developer Tools and...

Add Dockerfile with multi-stage build. Add docker-compose.yaml to run pg_embedding easily.

[Feature]: Support for DeepGEMM

4

### 🚀 The feature, motivation and pitch We noticed that DeepSeek has recently released [DeepGEMM](https://github.com/deepseek-ai/DeepGEMM), a specialized library for accelerating GEMM operations. Given vLLM is focus on computational optimization, are...