vLLM首日支持MiniMax-M3.1-Flash
vLLM Blog 称已首日支持 MiniMax-M3.1-Flash，可运行于 NVIDIA Blackwell GPU、配备专用内核的 NVIDIA Rubin GPU，以及 AMD MI350 系列 GPU，并提供 NVIDIA 和 AMD 的预构建镜像。实现采用 MiniMax Sparse Attention、NVFP4 KV 缓存、NVFP4 量化 MoE 权重和 DSpark drafter。vLLM 报告了内核与服务性能提升，其中包括在 GB300、Rubin 和 MI355X 上的智能体服务优化。报告还称已提供基于 veRL、FSDP2 和 LoRA 的首日端到端强化学习支持，其演示使用了 16 张 GB300 GPU。
此次集成为该模型提供了覆盖 NVIDIA Blackwell、NVIDIA Rubin 和 AMD MI350 系列硬件的优化推理路径。强化学习支持及相关结果仅在 NVIDIA GB300 系统上进行演示。
MiniMax-M3.1-Flash is the latest model in the MiniMax-M3 family, with improvements across reasoning, coding, agentic, and visual tasks. It is also built for inference efficiency, with a native NVFP4 KV cache, NVFP4-quantized MoE weights, and a DSpark draft model for speculative decoding.
vLLM supports MiniMax-M3.1-Flash on day 0 on NVIDIA Blackwell GPUs, on NVIDIA Rubin GPUs with dedicated Rubin kernels, and on AMD MI350-series GPUs, with strong performance on agentic workloads.
TL;DR
- MiniMax Sparse Attention (MSA) with an NVFP4 KV cache for both the indexer and the attention path, plus NVFP4 MoE weights and a DSpark drafter.
- Blackwell MSA kernels use the new CUDA 13.4
QMUL4instruction to dequantize NVFP4 into FP8 inside the kernel: up to 1.7× faster indexer QK decode and 1.3× faster sparse attention decode. - NVFP4 MegaMoE with MXFP8 shared-expert fusion and early TMEM release: 20% lower kernel latency in prefill and 7% higher prefill throughput.
- Indexer decode context parallelism (DCP): up to 3.3× faster indexer per sparse layer at 512K context on 4× GB300.
- QKV GEMM + norm + RoPE + KV-insert fusion: 1.1–1.6× faster prefill at 512+ tokens and about 19% lower P50 TTFT at TP4.
- FlashInfer PrimiTS backend for the DSpark drafter attention: 1.3–2× faster than FlashAttention 4, 5% lower total forward time.
- Rubin (SM107) MSA kernels are also integrated into vLLM with state-of-the-art performance.
- AMD MI350 series: the NVFP4-native MSA kernel, indexer decode context parallelism, dual-batch overlap, and the mono kernel deliver a 2–3× performance boost across the board.
- Agentic Serving: on NVIDIA GB300, up to 418.9 tok/s per user at the latency-sensitive end; on NVIDIA Rubin, up to 724.9 tok/s per user and 191.5K total tok/s per GPU; on AMD MI355X, up to 133.3M total tokens per dollar of TCO on the SemiAnalysis AgentX benchmark.
- Day-0 RL support: end-to-end RL with veRL, FSDP2, and LoRA on the NVFP4 checkpoint.
#MiniMax-M3.1-Flash#vLLM#MiniMax#NVIDIA Blackwell#NVIDIA Rubin#AMD MI350#MiniMax Sparse Attention#DSpark