Rebuilding GPT2 inference in ~500 lines of (commented) code

Similar products

by description similarity

1. Speeding up LLM inference 2x times (possibly)

   asciinema.org

   Here's a project I've been working on for the last few months.

   HNHacker News419 pts

2. Inferbench

   inferbench.com

   collect/share datapoints on GPU's inference performance

   HNHacker News7 pts

3. Finetune a Gemma 2B model for codegen

   github.com

   Supervised fine-tuning of Google's open-source Gemma-2B model to optimize writing Python code

   HNHacker News5 pts

4. IPython-GPT

   github.com

   a Jupyter/IPython Interface to Chat GPT

   HNHacker News144 pts

5. Cursor

   cursor.so

   IDE built for coding with GPT-4

   HNHacker News9 pts