vLLM to Natively Support Kimi K3 at Launch
AccBalanced · x · 2026-07-17
The vLLM team congratulated Moonshot AI on the release of Kimi K3 and announced a partnership between the two. Moonshot AI contributed the implementation code for KDA (Kimi Delta Attention) prefix caching to vLLM, breaking traditional prefix caching assumptions and enabling the open-source community to efficiently serve long-context inference on day one. vLLM will natively support Kimi K3 at launch, with the model weights scheduled to be open-sourced on July 27, 2026.
More from Infra
- RTK Terminal Compression Cuts Tokens but Leaves Your AI Coding Bill Unchanged — Bartaseth · 2026-09-11
- SF Compute founder: buying compute is 'an absolutely awful experience' right now — IgorCarron · 2026-09-11
- SmolVM open-sources persistent computer infrastructure for agents that outlive chat sessions — aniketmaurya · 2026-09-11
- PyTorch Day Korea 2026 launches first offline conf, CFP closes Sept 13 — PyTorch · 2026-09-11
- Local LLM server dilemma: 4x CMP-170HX (price up 53% in 20 days) vs Mac Studio M5 Ultra — rumboll · 2026-09-11
- llama.cpp lands Flash Attention tuning for RDNA4, big prefill gains on AMD — pmttyji · 2026-09-11