vLLM ecosystem ships d3-turbo: multimodal decision model, 15x faster, tops Jev Decision Index
vllm_project · x · 2026-10-20
The vLLM project highlighted d3-turbo from the vllm-sr team, a new SOTA multimodal foundation decision model for intelligent routing.
Key facts:
- Ranks #1 on both Jev Decision Index boards; can point (box), follow instructions, and see images in questions.
- StateOnce brings 15x speedup over d3 flash.
- Weights are open on Hugging Face (vllm-sr/d3-turbo); its chat template supports xhigh/medium/low reasoning effort levels, defaulting to xhigh.
More from coding & agent
- Microsoft's TokenEconomizer cuts coding agents' recurring token costs with a black-box controller — MicrosoftResearch · 2026-10-20
- User: Codex burns half of the day's usage limits within an hour after banked reset — ssh4net · 2026-10-20
- Berth: a Go binary that time-shares one GPU between AI engines and games via leases — Distinct-Pie2389 · 2026-10-20
- Building Tools Inside Tools to Build the Tool: Game Dev's Inception — eschadiol · 2026-10-20
- reuF2F: 244 open math problems formalized in Lean, best coding agent solves only ~40% — AkariAsai · 2026-10-20
- When should an agent combine tool readings without a shared snapshot? — InformationLive493 · 2026-10-20