Efficient Triton Kernels for LLM Training

finetuning gemma2 llama llama3 llm-training llms mistral phi3 triton triton-kernels
1 Open Issue Need Help Last updated: Dec 2, 2024

Open Issues Need Help

View All on GitHub

AI Summary: Add support for the SmolLM3 model to the Liger Kernel library by implementing necessary patching APIs and kernels to optimize its performance, similar to existing support for other LLMs like LLaMA and others. This involves adapting the existing framework to handle the specific architecture and operations of SmolLM3.

Complexity: 4/5
good first issue huggingface

Efficient Triton Kernels for LLM Training

Python
#finetuning#gemma2#llama#llama3#llm-training#llms#mistral#phi3#triton#triton-kernels