TokenSpeed ships Day-0 support for MiniMax M3.1 Flash with ~3× faster inference
zhyncs42 · x · 2026-10-23
- TokenSpeed announced Day-0 support for MiniMax M3.1 Flash and is featured in MiniMax's official deployment guide.
- Key techniques: DSpark speculative decoding plus MXFP8/NVFP4 mixed precision on Blackwell GPUs; MiniMax reports nearly 3× faster online inference vs the previous generation.
- The HF model config also reveals conventions like XML-rendered tool calls and omitting None fields entirely.
More from Infra
- Inco Open-Sources DFlash 2 Drafter: Lossless 3.5× Speedup for MiniMax M3.1 Flash — Lianhuiq · 2026-10-23
- vLLM details M3.1 Flash serving: NVFP4 cuts weights 44.6%, boosts capacity 2.7x — vllm_project · 2026-10-23
- M3.1 Flash hits 191.5k tok/s per GPU on Vera Rubin NVL72, leads open models on agent benchmarks — vllm_project · 2026-10-23
- Agents that don't close connections on retry waste ~148 tokens per task, vLLM tests show — No-Peanut-6988 · 2026-10-23
- Ex-Googler with 35 Years in Software Pursues Local AI Coding and Music Video Generation — julianharris · 2026-10-23
- Intelligence too cheap to meter: Opus price down 4x while AA score jumps 21 to 58 — haider1 · 2026-10-23