warlockedward issues

Results 13 issues of


                                            warlockedward

希望知识库的网络地址能支持微软的confluence登录，并下载页面内容

**例行检查** [//]: # '方框内填 x 表示打钩' - [x] 我已确认目前没有类似 features - [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 features，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 features 可能会被无视或直接关闭** **功能描述** 目前的知识库针对网络页面的下载无法支持有登入情况的页面下载内容方式 **应用场景** 企业大量的文档或者知识库都保存在特定的网络空间内，如使用微软认证的confluence，对于下载相关页面信息失败，希望能有接口可以处理类似的任务...

feature

[Bug]: As V100 does not support FlashAttention, it is not possible to run the gemma model, hopefully it can support the xformers way to run it

### Your current environment ```text The output of `python collect_env.py` ``` ### 🐛 Describe the bug python3 -m vllm.entrypoints.openai.api_server --model /model/models/gemma-2-27b-it/ --dtype float16 --gpu-memory-utilization 0.98 --dtype float16 --port xxxxxx --tensor-parallel-size...

bug

OpenAI Base_url and Model Definition

**Is your feature request related to a problem? Please describe.** A clear and concise description of what the problem is. Ex. I'm always frustrated when [...] When nothing but defining...

enhancement

[Feature]: Reflection-Llama-3.1-70B tool-choice support

### 🚀 The feature, motivation and pitch Would like to implement Reflection-Llama-3.1-70B's tool-choice ability to provide ### Alternatives _No response_ ### Additional context _No response_ ### Before submitting a new...

feature request

marker-pdf 打开--use_llm选型

**例行检查** [//]: # '方框内填 x 表示打钩' - [ ] 我已确认目前没有类似 features - [ ] 我已确认我已升级到最新版本 - [ ] 我已完整查看过项目 README，已确定现有版本无法满足需求 - [ ] 我理解并愿意跟进此 features，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 features 可能会被无视或直接关闭**...

Support LLM/Model Caching

[Feature]: S1-32B Reasoning Parser support

### 🚀 The feature, motivation and pitch While S1 recognizes logical structures in legal texts, its reasoning is somewhat unstructured. ### Alternatives this is my code with s1 parser #...

feature request

stale

warlockedward