TokenSpeed adds Day-0 support for Qwen 3.8 Flash Next architecture
Alibaba_Qwen · x · 2026-08-27
Inference platform TokenSpeed announced Day-0 support for the Qwen 3.8 Flash Next model. The integration covers key architectural features including:
- GDN + Qwen Sparse Attention hybrid architecture
- Gated residual connections
- N-gram embedding
Notably, TokenSpeed supports FP8 precision for N-gram embedding. The team stated they will continue optimizing beyond Day-0 as a preview for Qwen 4.
More from Infra
- Video generation speeds: 23.7s vs 11m shows Jevons Paradox in action — gorkem · 2026-08-27
- The Guardian podcast: Everyone hates datacentres, but do we really need them? — nordicinst · 2026-08-27
- Analyze Nvidia Strategy: Buybacks vs. Heavy HBM Investment — toptickcrypto · 2026-08-27
- Z.ai serving 100T tokens/day on Chinese hardware implies training capability — SumitGup · 2026-08-27
- DLSS 4.5 Ray Reconstruction released with 2nd-gen joint denoiser — ctnzr · 2026-08-27
- Startups may measure runway in tokens by 2027 — MillionInt · 2026-08-27