1.3K views · 16 likes · 2 reposts (at collection)
vLLM adds Day-0 support for Step 5 Preview
- Who
- vLLM
- What
- shares a technical overview of Step 5 Preview Day-0 support in vLLM, including sparse attention, MoE, multi-token prediction, vision, and serving work across Blackwell and Hopper
What happened
🎉 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, with kernel results and further details at
Links in the post: 1The story so far
vLLM announced Day-0 support for Step 5 Preview, covering sparse attention, mixture-of-experts (MoE), multi-token prediction and vision, with serving work across Blackwell and Hopper hardware. vLLM said the implementation spans the sparse indexer, FP8 MegaMoE and cache transfer, and shared a technical overview with kernel results.
Keep reading
Latest daily · Issue 24NVIDIA and AI4Bharat Introduce Nemotron-pretraining-Indic-v1 and an Open Data Generation PipelineTrending now
- 1Meta Releases Muse Spark Open With Mac and Cloud Support, Topping US Open-Weight Index
- 2Google Launches Gemini 4 Argon Globally, Expands Paid Access as Benchmark Results Vary
- 3OpenAI Updates GPT-6 Astra Pro in ChatGPT With Parallel Agents and Faster Responses
- 4Meta’s New Business Terms Raise Dispute Over Website Crawling and AI Training Rights
Tomorrow at 08:00, a briefing like this arrives in your inbox.
The same kind of briefing as the one above: a few stories worth reading. Free. Mail starts after you confirm, and every letter has a one-click unsubscribe. Read a past issue · 2026-10-17