DNeo: Better Target Feature Encoding Speeds Up Speculative-Diffusion LLM Inference
cerebras · hf · 2026-11-19
The DNeo paper on Hugging Face proposes a lightweight feature-encoding method with rejection memory and architectural enhancements, accelerating LLM inference by improving the verification of speculative-diffusion draft models.
More from Infra
- vLLM v0.34.0 Lands: 1,061 Commits, Up to 1.95x Faster Decode on GB200 — vllm_project · 2026-11-19
- Cascade MoE on Bittensor beats Salesforce's Moirai2 on GIFT-Eval 19 days after launch — const_reborn · 2026-11-19
- Sciforium hits 1,129 output tokens/sec P90 on DeepSeek-V4.1-Flash over 4 AMD MI355X GPUs — rohanpaul_ai · 2026-11-19
- Running untrusted agents on GKE: sandboxing, cold starts, and state — rseroter · 2026-11-19
- OpenAI models find up to 14% PPA gains on AMD GPU IP, improve custom Jalapeño chip — OpenAI · 2026-11-19
- A Local Model for Every Device: 6 Free Offline Models from Phones to Servers — alex_verem · 2026-11-19