Search results for “speculative decoding”

Matching articles

TECH14 hours ago

GPT-5.6 Gets a Major Price Cut Starting Today, Up to 80% Off

TECH22 hours ago

Chinese AI competitors may have forced OpenAI’s hand on pricing

TECHyesterday

OpenAI’s ChatGPT 5.6 Sol Cuts AI Serving Costs by 20 Percent

TECHyesterday

Tencent Open-Sources AngelSpec: A Unified Training Framework for MTP and Block-Parallel Speculative Decoding on Hy3 Models

TECHyesterday

GPT-5.6 Has Confirmed to Optimize Itself: A New Left-Foot-Stepping-on-Right-Foot Trick Has Appeared

TECHyesterday

OpenAI autonomously improved GPT-5.6's inference efficiency using GPT-5.6 itself

PAPER2 days ago

Revisiting Lossy Verification in Speculative Decoding: Mechanisms, Trade-offs, and Failure Modes

TECHJuly 11, 2026

Hardware-Aware, Dynamic Speculative Decoding (DSD) | Cohere

PAPERJune 2, 2026

Domino: Decoupling Causal Modeling from Autoregressive Drafting in Speculative Decoding

Hugging Face Papers

PAPERMay 28, 2026

Fast-dDrive: Efficient Block-Diffusion VLM for Autonomous Driving

Hugging Face Papers

TECHMay 27, 2026

Meet EAGLE 3.1: The Speculative Decoding Algorithm That Fixes Attention Drift in LLM Inference

TECHMay 27, 2026

Eagle 3.1: Collaboration Between the EAGLE Team, vLLM Team, and TorchSpec Team | Hacker News