Article · MarkTechPost · Tuesday 3 November

NVIDIA Shows 3 Ways to Speed Up MoE Inference on DGX Spark, Lifting Ling-3.0-flash Throughput 42.5%

NVIDIA shows how 3 stacked optimizations speed up MoE inference on a single DGX Spark. On Ant Group inclusionAI's 124B Ling-3.0-flash, GSM8K decode throughput rose 42.5% with no detectable accuracy change.

Read at marktechpost.com The opening of the article at marktechpost.com.

In this story

Repoinclusionai/ling-cookbook

A tool or model opens in the Heidelberg AI Curriculum: what it does, what it costs, how to start. A repo opens on GitHub.

More from MarkTechPost

All stories

ArticleMarkTechPost

Together AI Releases Together Compiler: Agents Make Inference Up to 2.6x Faster

Together AI released Together Compiler, an agent-driven loop that keeps re-optimizing the inference forward pass as traffic shifts. It beat the best InferenceX configurations by up to 2.6x TPS in under 24 hours per model.

12 h ago

ArticleMarkTechPost

Google AI Research Releases Agile Deliberation Framework for Gray-Area Image Classifiers

Google Research released Agile Deliberation, a human-in-the-loop framework that helps users define subjective visual concepts through borderline images. In 18 live sessions, it lifted Gemini-based classifier F1 by 10.5 points over zero-shot.

Repogoogle-research/google-research

15 h ago

ArticleMarkTechPost

webAI Releases TwIL-8B, an 8.8B Reasoning Model Scoring 98.2 on MATH-500

webAI released TwIL-8B, an 8.8B reasoning model post-trained from IBM Granite 4.2 8B. It posts 98.2 on MATH-500 and 81.6 on LiveCodeBench, but trails similar-size models on knowledge benchmarks.

22 h ago

ArticleMarkTechPost

Ricursive AI Releases Ripple-65B Preview: A 65B Dense Open-Weight Model Scoring 80.5 on Terminal-Bench 2.1

Ricursive Intelligence released Ripple-65B Preview, a 65B dense open-weight LLM under Apache 2.0. It scores 80.5 on Terminal-Bench 2.1, ahead of US open models up to 15x its size.

23 h ago