EAGLE 3.1: Advancing Speculative Decoding Through Collaboration Between the EAGLE Team, vLLM, and TorchSpec
The EAGLE team, in collaboration with vLLM and TorchSpec, releases EAGLE 3.1, which significantly improves speculative decoding robustness and acceptance length in long-context and varied chat scenarios by addressing the 'attention drift' problem.
vLLM Blog · May 26, 2026