692: Lossless LLM Weight Compression: Run Huge Models on a Single GPU

Join Jon as he navigates listeners through the innovative SpQR approach—a cutting-edge, lossless LLM weight compression technique that harnesses the power of quantization. Tune in as Jon delves into the four steps behind this groundbreaking method in this week's episode.Additional materials: www.superdatascience.com/692Interested in sponsoring a SuperDataScience Podcast episode? Visit JonKrohn.com/podcast for sponsorship information.