Consistency LLM: converting LLMs to parallel decoders accelerates inference 3.5x
4 hours ago (hao-ai-lab.github.io)
4 hours ago (hao-ai-lab.github.io)
9 hours ago (blog.google)
3 hours ago (seriouseats.com)
2 days ago (core77.com)
3 days ago (ifesunmola.com)
2 days ago (32by32.com)
3 hours ago (research.google)
10 hours ago (github.com)
7 hours ago (grafychat.com)
7 hours ago (chromakode.com)
3 hours ago (ycombinator.com)
1 hour ago (simbricks.github.io)
3 days ago (climbing.ai)
2 days ago (hakaimagazine.com)
2 days ago (github.com)
2 days ago (github.com)
2 days ago (collectorsweekly.com)
4 hours ago (researchsquare.com)
7 hours ago (pitchfork.com)
11 hours ago (github.com)
13 hours ago (github.com)
8 hours ago
3 hours ago (secretnyc.co)
10 hours ago (newatlas.com)
3 days ago (faultlore.com)
7 hours ago (github.com)
6 hours ago (openai.com)
10 minutes ago (jacobin.com)
2 days ago (youtube.com)
2 days ago (github.com)