chenwanqq

Hello, I've created a pull request #287 to support Baidu Qianfan Platform.I would greatly appreciate it if you could take some time to review the code and provide feedback. Hail...

Hello llm-chain maintainers, I have been working on integrating Baidu Qianfan (also known as ernie/Wenxin) platform into llm-chain project, and I believe this addition will greatly enhance our project's capabilities....

Add LLaVA Support

6

## Introduction This implementation is based on my work for [candle](https://github.com/huggingface/candle). However, it incorporates some notable differences: * I have completely removed support for the model format used in the...

Is it advisable to avoid variable shadowing when using Candle?

1

### Discussed in https://github.com/huggingface/candle/discussions/2272 Originally posted by **chenwanqq** June 19, 2024 Considering following facts: * Rust doesn't have a garbage collector. * Variable shadowing does **not** release memory (drop) within...

Any plan about KV compression algorithm like SnapKV and PyramidKV?

4

Hi, I'm wondering if you have any plans regarding kv compression methods like SnapKV and PyramidKV. These methods can reduce the use of memory for KV cache, hence improving availability...