1 LLM speculative decoding explained simply (jwlabs.vercel.app) 20 hours ago shreybirmiwal vercel.app
13 Predictive Speculative KV Replication for Bursty LLM Inference (jwlabs.vercel.app) 21 hours ago shreybirmiwal vercel.app
1 Specializing Speculative Decoding to increase drafter accuracy (jwlabs.vercel.app) a day ago shreybirmiwal vercel.app