vLLM/Recipes
inclusionAI

inclusionAI/Ling-2.6-1T

Ling-2.6-1T (BailingMoeV2_5) FP8 instruct model with 1T total / 50B active params, hybrid linear + MLA attention, 128K context

View on HuggingFace
moe1T / 50B131,072 ctxvLLM nightly+text