vLLM's push-based NIXL KV transfer over RDMA cuts TTFT and TPOT for disaggregated inference
vLLM Blog · rss · 2026-10-14
The vLLM blog details a push-based NIXL connector for disaggregated serving: the prefill instance writes KV cache directly into decode memory over RDMA, removing router relay, decode-side allocation, and transfer setup from the TTFT critical path — improving both TTFT and TPOT. Directly relevant for teams running large-scale prefill/decode disaggregation.
More from Infra
- OpenJet claims Qwen3.8-27B coding runs 1.9x faster than llama.cpp on one RTX 3090 — JeremyCMorgan · 2026-10-23
- Jensen Huang lays out NVIDIA's full Vera Rubin agentic system: NVL72, MGX, CMX and RTX — rohanpaul_ai · 2026-10-23
- Jensen Huang details Vera Rubin agentic stack: NVL72, MGX, CMX and RTX — rohanpaul_ai · 2026-10-23
- ONNX to Transformers.js: running models directly in your browser — JosephJacks_ · 2026-10-23
- MiniMax M3.1 Flash free for 3 days on 0G, with 1M context and 512K output — MiniMax_AI · 2026-10-23
- "We bet on Cloudflare and it paid off": R2 and D1 at billion scale — dinasaur_404 · 2026-10-23