SpecOPD: Branch-Parallel On-Policy Distillation for Speculative Decoding
cs.AI
Submitted: 2026-11-02
Updated: 2026-11-02
Code: https://github.com/z-lab/dflash
Terminology
Sources
- Accelerating Large Language Model Decoding with Speculative Sampling
- DFlash: Block Diffusion for Flash Speculative Decoding
- Draft-OPD: On-Policy Distillation for Speculative Draft Models
- Breaking Entropy Bounds: Accelerating RL Training via MTP with Rejection Sampling
- Gated Delta Networks: Improving Mamba2 with Delta Rule
- On the Design of Qwen3.8-Next Architecture: Evaluation, Efficiency, and Training Stability
- Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena
- Evaluating Large Language Models Trained on Code
- SWE-bench: Can Language Models Resolve Real-World GitHub Issues?
- Terminal-Bench: Benchmarking Agents on Hard, Realistic Tasks in Command Line Interfaces
- DSpark: Confidence-Scheduled Speculative Decoding with Semi-Autoregressive Generation
- EAGLE: Speculative Sampling Requires Rethinking Feature Uncertainty
- EAGLE-3: Scaling up Inference Acceleration of Large Language Models via Training-Time Test
- Better & Faster Large Language Models via Multi-token Prediction
- DeepSeek-V3 Technical Report
- PARD: Accelerating LLM Inference with Low-Cost PARallel Draft Model Adaptation
- P-EAGLE: Parallel-Drafting EAGLE with Scalable Training
- DFlare: Scaling Up Draft Capacity for Block Diffusion Speculative Decoding
- Domino: Decoupling Causal Modeling from Autoregressive Drafting in Speculative Decoding
- Medusa: Simple LLM Inference Acceleration Framework with Multiple Decoding Heads
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