Popular repositories

1. lorax lorax Public

   Multi-LoRA inference server that scales to 1000s of fine-tuned LLMs

   Python 1.6k 108

2. llm_distillation_playbook llm_distillation_playbook Public

   Best practices for distilling large language models.

   Jupyter Notebook 282 21

3. lora_bakeoff lora_bakeoff Public

   Python 5 1

4. neuropod neuropod Public

   Forked from uber/neuropod

   A uniform interface to run deep learning models from multiple frameworks

   C++ 3 2

5. punica punica Public

   Forked from punica-ai/punica

   Serving multiple LoRA finetuned LLM as one

   Cuda 2 1

6. json-mode-benchmark json-mode-benchmark Public

   Jupyter Notebook 2