🎉 Step 5 Preview has Day-0 support in vLLM.
Sparse attention, MoE, multi-token prediction and vision, with serving work across Blackwell and Hopper.
The work spans the sparse indexer, FP8 MegaMoE and cache transfer. Here is how the pieces fit together, with kernel results and validation below. 🧵
1/6
vLLM adds Day-0 support for the Step 5 Preview model
AISummary
vLLM says Step 5 Preview has Day-0 support, covering sparse attention, MoE, multi-token prediction, and vision. The work includes serving on Blackwell and Hopper GPUs, a sparse indexer, FP8 MegaMoE, and cache transfer. The post is the first in a six-part thread with kernel results and validation details.
Post on XView on X
vLLMVerified on X
@vllm_project
Source: vLLM · x.comPublished