nullname
nullname
In #45, we talk about add the sqlite as an alternative database for some budget machine, here's a quick implementation, detailed changes: 1. Add sqlite database for local use only,...
Recently, I found this awesome project which can integrate the chatgpt into teleggram, and I was instantly install and run it on some of my server which run pretty good....
In #5292, we've requested to increase the `threads_batch` in ui to allow `> 32` threads, and here's the PR, to enlarge it. Minor changes, tested on my rig with `llama.cpp`...
int fill(int blockNum) (com_tencent_wstt_gt_api_utils_MemFillTool.c@50) Using crt func will significantly speed up the zero operation ref: [calloc](http://en.cppreference.com/w/c/memory/calloc) [memset](http://en.cppreference.com/w/c/string/byte/memset)
# Description Add some patches to fix the ethernet PHY on orangepi zero2w, includes: - `drv-pwm-sun50i-h616-enhance-pwm.patch` - sunxi pwm enhance driver from this commit: [linux-orangepi#c68ef342eba3673c7f1f5aa1ab819b06da1f60c6](https://github.com/orangepi-xunlong/linux-orangepi/commit/c68ef342eba3673c7f1f5aa1ab819b06da1f60c6#diff-655f363e0dfd457701c5f8b70e429545dadee9132a0fa10d55649e6b4ed1700b) - `drv-pwm-sun50i-h616-enhance-pwm.patch` - sunxi gmac...
[WIP]backend: Integrating QNN (Qualcomm AI Engine Direct) as a dedicated backend for Qualcomm NPUs
**Warning: This is an early draft of my fork and will continue to be updated to meet the requirements in the [contributing guidelines](https://github.com/ggml-org/llama.cpp/blob/master/CONTRIBUTING.md)** ## Summary This fork is based on...