Tagged articles

LLM Acceleration

3 articles · Page 1 of 1

Jun 27, 2026 · Artificial Intelligence

DSpark in DeepSeek V4 Cuts LLM Inference Latency by Up to 85%

DeepSeek V4’s DSpark adds a speculative decoding framework that combines a lightweight draft model, semi‑autoregressive generation, and confidence‑scheduled verification, delivering 60‑85% faster inference for Qwen3 and Gemma models while providing an open‑source DeepSpec toolkit for training and evaluation.

Confidence-Scheduled VerificationDSparkDeepSeek

0 likes · 7 min read

DSpark in DeepSeek V4 Cuts LLM Inference Latency by Up to 85%

Old Zhang's AI Learning

May 14, 2026 · Artificial Intelligence

Boost Qwen3.6 with MTP: 1.5× Faster Local Deployment for Claude Code

The article explains how to enable Multi‑Token Prediction (MTP) in Qwen3.6 using a specific llama.cpp PR, achieving up to 1.5× faster local inference, details compilation steps, optimal parameters, memory requirements, and how to integrate the accelerated model with Claude Code while avoiding common pitfalls.

Claude CodeLLM AccelerationMTP

0 likes · 11 min read

Boost Qwen3.6 with MTP: 1.5× Faster Local Deployment for Claude Code

Tencent Technical Engineering

Jan 13, 2026 · Artificial Intelligence

Boost LLM Inference 1.9× with AngelSlim’s Speculative Decoding (Eagle3)

AngelSlim introduces a system‑wide speculative decoding framework called Eagle3 that combines lightweight draft models with parallel verification by large models, delivering up to 1.9× faster inference across LLM, vision‑language, and speech tasks while remaining open‑source and deployment‑ready.

AngelSlimEagle3LLM Acceleration

0 likes · 9 min read

Boost LLM Inference 1.9× with AngelSlim’s Speculative Decoding (Eagle3)