vLLM ships day-0 support for Kimi K3.1 across NVIDIA, AMD and TPUs
vllm_project · x · 2026-11-05
The vLLM project announces day-0 platform support for Kimi K3.1, spanning NVIDIA GPUs (including Vera Rubin), AMD Instinct MI355X, Google Cloud TPUs, plus Zhenwu 810e and M890.
Ready-to-use launch images include NVIDIA CUDA 13.0 and 13.4 variants and an AMD ROCm build. Built with Moonshot AI, Inferact and the vLLM community, the release also includes day-0 RL support via vLLM + Megatron — Inferact's work covers training–inference consistency for Kimi Delta Attention plus the cache/state management needed to serve long-running agents. From serving the model to continuing its training, the open stack is ready.
Related event: vLLM Ships Day-0 Support for Kimi K3.1 Across Training and Serving(5 posts)→
More from Infra
- Bittensor's Targon hits record $1.2M October revenue, first $1M month — markjeffrey · 2026-11-05
- Arohan: if training has any moat, it's space itself — _arohan_ · 2026-11-05
- Frontier training without megacampuses: MoE model trained across <20MW clusters over 25Gbps — _arohan_ · 2026-11-05
- LFM3-Omni-2B ported to run fully offline on iPhone at ~80 tok/s via custom WebGPU kernels — victormustar · 2026-11-05
- Solo dev's open-source browser agent uses local models to watch your screen and trigger actions — Roy3838 · 2026-11-05
- Mistral Large 4 1T hits HF Inference Endpoints at $10/hr on 4x A100 — ngxson · 2026-11-05