Split-KV: Efficient Context Parallelism for Training Diffusion Drafters
cs.AI
Submitted: 2026-11-04
Updated: 2026-11-04
Code: https://github.com/zxgx/verl
Terminology
Sources
- LV-XAttn: Distributed Cross-Attention for Long Visual Inputs in Multimodal Large Language Models
- Accelerating Large Language Model Decoding with Speculative Sampling
- DFlash: Block Diffusion for Flash Speculative Decoding
- Flex Attention: A Programming Model for Generating Optimized Attention Kernels
- Domino: Decoupling Causal Modeling from Autoregressive Drafting in Speculative Decoding
- RoBERTa: A Robustly Optimized BERT Pretraining Approach
Related papers
- Multi-Objective Structured Pruning of LLMs for Latency and Model Size Optimization
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Embeddings for Preferences, Not Semantics
- Can We Trust Item Response Theory for AI Evaluation?
- Diagnosing Task Insensitivity in Language Agents