Double: Breaking the Acceleration Limit via Double Retrieval Double: Breaking the Acceleration Limit via Double Retrieval Speculative Parallelism Paper • 2601.05524 • Published Jan 9 • 1
Double: Breaking the Acceleration Limit via Double Retrieval Speculative Parallelism Paper • 2601.05524 • Published Jan 9 • 1
Speculative Decoding via Hybrid Drafting and Rollback-Aware Speculative Decoding via Hybrid Drafting and Rollback-Aware Branch Parallelism Paper • 2506.01979 • Published May 16, 2025 • 1
Speculative Decoding via Hybrid Drafting and Rollback-Aware Branch Parallelism Paper • 2506.01979 • Published May 16, 2025 • 1
Double: Breaking the Acceleration Limit via Double Retrieval Double: Breaking the Acceleration Limit via Double Retrieval Speculative Parallelism Paper • 2601.05524 • Published Jan 9 • 1
Double: Breaking the Acceleration Limit via Double Retrieval Speculative Parallelism Paper • 2601.05524 • Published Jan 9 • 1
Speculative Decoding via Hybrid Drafting and Rollback-Aware Speculative Decoding via Hybrid Drafting and Rollback-Aware Branch Parallelism Paper • 2506.01979 • Published May 16, 2025 • 1
Speculative Decoding via Hybrid Drafting and Rollback-Aware Branch Parallelism Paper • 2506.01979 • Published May 16, 2025 • 1