vLLM Adds Support for Cohere2MoE Eagle3 Auxiliary States
September 17, 2026
The vLLM inference runtime now supports Cohere2MoE Eagle3 auxiliary hidden states. This integration enables more efficient inference for specific Mixture-of-Experts architectures.
HOW THIS AFFECTS YOU
●
builderYou can now run Cohere2MoE models with improved performance using the vLLM runtime.