#ring-attention

2 articles

01 ·Inference & Serving·★ MEMBER·PAPER·10 min read Paper Walkthrough: Online Draft Co-Training for Speculative Decoding in Large-Scale, Long-Context RL Post-Training — training the draft alongside a 122B policy at 256K tokens Rollout generation dominates RL post-training time. NVIDIA speeds it up with speculative decoding and keeps training the draft model alongside the policy — and shows how to get past the two walls that context parallelism and pipeline parallelism put in the way. A from-scratch walkthrough grounded in the paper text. 02 ·How Transformers Work·★ MEMBER·PAPER·11 min read How Long-Context LLMs Work — From RoPE Interpolation to Ring Attention A "128K context window" is two different walls, knocked down by two unrelated families of tricks. This walks through positional interpolation, NTK-aware scaling and YaRN for the position wall; sliding windows and ring attention for the compute wall; and how to read a needle-in-a-haystack chart without being fooled by it.