James Brown

Allow custom python interpreter to be specified by path

1

There are multiple python implementations such as `pypy`, `jython`, `ironpython`, `rustpython` etc. Also user may use different python interpreters under different `conda` or `venv` environments. Adding this configuration using config...

可以支持直播推流协议么

4

直播推流可以用rtmp

### 先决条件 (Prerequisites) - [X] 我已确认这个镜像源从未在 [其他 issues](https://github.com/tuna/issues) 中讨论过。 I am sure that this repo has NEVER been discussed in [other issues](https://github.com/tuna/issues). - [X] 我已确认这个镜像源没有我选择的镜像站上线。 I am sure that this...

Documentation typos, taking `tinydb` as `tinyflux`

1

**Describe the bug** Some documentation pages of this project have errors in example code snippets, and more accurately `tinydb` is used instead of `tinyflux`. You can search for all occurances...

是否可以启动一个后台服务 类似于appium或者airtest 用电脑远程操控autox

4

用adb启动autox的服务器 获取ip地址和端口号 pc连接并发送js代码并运行

Using backend 'xvnc' emits error 'Unrecognized option: -SecurityTypes'

3

Code: ```python from pyvirtualdisplay import Display with Display(backend='xvnc') as disp: ... ``` Error: ``` start failed 10 Traceback (most recent call last): File "/usr/local/lib/python3.9/dist-packages/pyvirtualdisplay/abstractdisplay.py", line 155, in start self._start1() File...

Support more AMD GPUs like `gfx90c`

5

`ollama` is using `llama.cpp` under the hood. Can trick `ollama` to use GPU but loading model taking forever. Procedures: - Upgrade to ROCm v6 - `export HSA_OVERRIDE_GFX_VERSION=9.0.0` Logs: ``` time=2024-03-10T22:51:10.851+08:00...

Pytest is the most popular testing framework in Python. I want to enhance its error logging, just like #76. Here's my code: ```python import better_exceptions from pytest import ExceptionInfo def...

This document is generated using: https://github.com/james4ever0/prometheous You can view the website at: https://james4ever0.github.io/RT-2/

[Core] Add retention policy code for processing requests

3

This pull request is intended to resolve the concurrency problem across various LLMs. It brings about two important configurable environmental variables: - VLLM_ENGINE_MAX_CONCURRENT_REQUESTS: Max concurrent requests to process at anytime,...