Hamid Shojanazeri 44ef280d31 adding flash attention and xformer memory efficient through PT SDPA		il y a 1 an
..
hf-text-generation-inference	b3067b55dc fix typos and spelling errors	il y a 1 an
README.md	3c84962685 adding checkpoint conversion	il y a 1 an
chat_completion.py	44ef280d31 adding flash attention and xformer memory efficient through PT SDPA	il y a 1 an
chat_utils.py	4767f09ecd Initial commit	il y a 1 an
chats.json	4767f09ecd Initial commit	il y a 1 an
checkpoint_converter_fsdp_hf.py	50e9d17045 add the default option for find the HF model_name/path from train_param.yaml	il y a 1 an
inference.py	44ef280d31 adding flash attention and xformer memory efficient through PT SDPA	il y a 1 an
model_utils.py	76a187c4d2 clean up	il y a 1 an
safety_utils.py	4767f09ecd Initial commit	il y a 1 an
samsum_prompt.txt	4767f09ecd Initial commit	il y a 1 an
vLLM_inference.py	4767f09ecd Initial commit	il y a 1 an

Inference

This folder contains inference examples for Llama 2. So far, we have provided support for three methods of inference:

inference script script provides support for Hugging Face accelerate, PEFT and FSDP fine tuned models.
vLLM_inference.py script takes advantage of vLLM's paged attention concept for low latency.
The hf-text-generation-inference folder contains information on Hugging Face Text Generation Inference (TGI).

For more in depth information on inference including inference safety checks and examples, see the inference documentation here.