cd/entity/Z-Lab· home› entities› Z-Lab
grep -l @z-lab /news/*.json | wc -l → 1

Z-Lab

mentions 1 type Organization feed RSS

// recent coverage 1 mentions

07:00
2026-07-02
dotnetperls.com
large-language-models

DFlash for Local LLM Inference

Z-Lab's DFlash technique uses diffusion models to accelerate LLM token generation through speculative decoding, achieving up to 123 tokens per second for code generation in tests with Qwen 3 8B on lla…

// co-occurs with top 3 entities
DFlash 1 Qwen 3 8B 1 llama-cpp 1
// topics top 4 topics
large language models 1 generative ai 1 ai research 1 ai infrastructure 1