GLM 5.3 open weights arrive; DFlash 2 speculative decoding hits 4.4x FP8 throughput
gan_chuang · x · 2026-08-29
Zhipu has released GLM 5.3 with open weights. Third-party team incoai shipped Day 0 support: a DFlash 2 speculative decoding drafter, an NVFP4 quantized checkpoint, and a live endpoint on TokenRouter's GB300s — claiming up to 4.4x the throughput of native FP8 under autoregressive decoding. As zhijianliu notes, DFlash 2 ten days ago was the first piece; GLM 5.3 completes the stack.
Related event: Z.ai Open-Sources GLM-5.3 and GLM-5.3-Flash(28 posts)→
More from Infra
- SK Hynix ties new US plant to looser chip equipment exports to China, sources say — pstAsiatech · 2026-10-15
- Perplexity's new embedding models: index with a 9B model, search with 0.6B — antoine_chaffin · 2026-10-15
- Unsloth ships GGUF quants for Nemotron 3.5: Bolt-74B runs in 24GB RAM — danielhanchen · 2026-10-15
- vLLM-Omni ships Day-0 serving for FLUX 3 Image Klein with BF16, FP8, NVFP4 support — vllm_project · 2026-10-15
- NVIDIA's Nemotron 3.5 Super VL lands training and inference support on Applied Compute — ypatil125 · 2026-10-15
- CoreWeave bond yield tops 16% as loans outlast customer contracts by ~2 years — tengyanAI · 2026-10-15