WeiguangHan

@hkvision Add whisper models into nightly test.

Just for test.

LLM: use pip to install bigdl-llm

3

@Oscilloscope98 Please have a look. Looking forward to your comments. Thanks!

MTL failed to run rwkv-4-world-7b: Failed to load libsycl-fallback-bfloat16.spv

1

MTL (Ultra 5 125H + 32GB 7467MHz) failed to run **rwkv-4-world-7b**.  Configured according to: https://ipex-llm.readthedocs.io/en/latest/doc/LLM/Quickstart/install_windows_gpu.html. The oneAPI is installed using pip installer. The commands I used are as follows....

LLM: add more info for env check script

3

Add more info for env check script.

Building Error with simple_knn and diff_gaussian_rasterization

1

I tried to set up the environment using the command `conda env create -f environment.yml`. But some errors occured. This is the log and setup of my machine. Thanks for...

请问Paddlespeech有支持Intel的GPU吗[e.g. Arc 770]

1

## General Question

如何让TTS生成女性声音

2

## General Question 目前TTS默认的是男性声音。如何让TTS生成女性声音，需要改哪里，大伙有懂得可以指导一下，

Inference speed and memory usage of Qwen1.5-14b

3

I have tested the inference speed and memory usage of Qwen1.5-14b on my machine using the example in ipex-llm. The peek cpu usage to load Qwen1.5-14b in 4-bit is about...