EPISODE · Jul 14, 2025 · 8 MIN
CCQ：压缩巨兽 - 两比特大语言模型的革命
from AI Podcast · host weedge
本期播客深入探讨了名为CCQ（卷积码量化）的突破性技术。面对大型语言模型（LLMs）日益增长的部署成本和障碍，CCQ提出了一种创新的极低比特量化方案。我们将讨论CCQ如何通过结合卷积码、混合编码和码簇等技术，在几乎不损失模型精度的前提下，将模型压缩至2.0到2.75比特。同时，我们也会探讨其独特的免查找表和位移解码设计如何解决了传统矢量量化的推理速度瓶颈，并实现了在单个GPU上部署超大型模型（如文心4.5）的壮举。欢迎收听，了解这项可能改变大模型部署格局的黑科技。
Embed this episode
Ready to play
CCQ：压缩巨兽 - 两比特大语言模型的革命
0:00
8:46
1×
No transcript for this episode yet
Similar Episodes
No similar episodes found.
Similar Podcasts
No similar podcasts found.
Frequently Asked Questions
How long is this episode of AI Podcast?
This episode is 8 minutes long.
When was this AI Podcast episode published?
This episode was published on July 14, 2025.
Can I download this AI Podcast episode?
Yes. Use the download control on the episode player to save the publisher-provided media file.
URL copied to clipboard!