vLLM ships Day-0 support for Tencent Hy4 Flash with 8x H200 deployment recipe

vllm_project · x · 2026-11-18

vLLM announces Day-0 support for Tencent's Hy4 Flash: a 220B-total-parameter (incl. 64B Engram embeddings) MoE with 12B active per token, 1M-token context and multimodal understanding, aimed at productivity and agent workflows.

Architecture: 42 decoder layers with hybrid sliding-window + compressed sparse attention, Latent MoE, Engram embeddings, and a five-layer DFly speculative decoding head (on by default). Deployment notes:

Original post →

More from Infra

Infra channel →