05dec7eda9
### What this PR does / why we need it? This PR refactor the user stories page: - Move it to community - Add initial info of LLaMA-Factory, Huggingface/trl, MindIE Turbo, GPUStack, verl - Add a new page for LLaMA-Factory ### Does this PR introduce _any_ user-facing change? No ### How was this patch tested? Preview locally Signed-off-by: Yikun Jiang <yikunkero@gmail.com>
1.1 KiB
LLaMA-Factory
About / Introduction
LLaMA-Factory is an easy-to-use and efficient platform for training and fine-tuning large language models. With LLaMA-Factory, you can fine-tune hundreds of pre-trained models locally without writing any code.
LLaMA-Facotory users need to evaluate and inference the model after fine-tuning the model.
The Business Challenge
LLaMA-Factory used transformers to perform inference on Ascend NPU, but the speed was slow.
Solving Challenges and Benefits with vLLM Ascend
With the joint efforts of LLaMA-Factory and vLLM Ascend (LLaMA-Factory#7739), the performance of LLaMA-Factory in the model inference stage has been significantly improved. According to the test results, the inference speed of LLaMA-Factory has been increased to 2x compared to the transformers version.
Learn more
See more about LLaMA-Factory and how it uses vLLM Ascend for inference on the Ascend NPU in the following documentation: LLaMA-Factory Ascend NPU Inference.