# grouped-query attention

Published articles for grouped-query attention.

This is one page of public article previews, not the complete archive. Follow Next page to continue. Summaries are not the original full articles.

## Granite 4.2 LLMs: How They're Built

DevFeed: [Granite 4.2 LLMs: How They're Built](<https://devfeed.tech/articles/granite-4-2-llms-how-they-re-built-7257.md>)

Original publisher: [Read original article](<https://huggingface.co/blog/ibm-granite/granite-4-2>)

Author: Yousaf Shah; Swanand Kadhe; Riddhiman Moulick; Ashish Sunil Agrawal; Santosh Borse

Published: 2026-08-25T15:14:14Z

Content type: article

Language: en

Sources: [Hugging Face - Blog](<https://devfeed.tech/sources/hugging-face-blog.md>)

Topics: [Language models](<https://devfeed.tech/topics/language-models.md>), [AI Chat](<https://devfeed.tech/topics/ai-chat.md>), [AI-assisted coding](<https://devfeed.tech/topics/ai-assisted-coding.md>), [releases](<https://devfeed.tech/topics/releases.md>)

Tags: [agentic](<https://devfeed.tech/tags/agentic.md>), [agents](<https://devfeed.tech/tags/agents.md>), [apache](<https://devfeed.tech/tags/apache.md>), [chain-of-thought](<https://devfeed.tech/tags/chain-of-thought.md>), [code](<https://devfeed.tech/tags/code.md>), [fine-tuning](<https://devfeed.tech/tags/fine-tuning.md>), [grouped-query-attention](<https://devfeed.tech/tags/grouped-query-attention.md>), [ibm](<https://devfeed.tech/tags/ibm.md>), [llms](<https://devfeed.tech/tags/llms.md>), [models](<https://devfeed.tech/tags/models.md>), [post-training](<https://devfeed.tech/tags/post-training.md>), [reasoning](<https://devfeed.tech/tags/reasoning.md>), [reinforcement-learning](<https://devfeed.tech/tags/reinforcement-learning.md>), [sglang](<https://devfeed.tech/tags/sglang.md>), [tool](<https://devfeed.tech/tags/tool.md>), [training](<https://devfeed.tech/tags/training.md>), [transformer-architecture](<https://devfeed.tech/tags/transformer-architecture.md>), [vllm](<https://devfeed.tech/tags/vllm.md>)

### AI overview

Granite 4.2 is a family of 3B, 8B, and 30B dense decoder-only reasoning language models. The article covers their training pipeline, thinking modes, native tool calling, and agentic reinforcement learning for the 8B and 30B models.

### Source excerpt

Authors: Granite Team, IBM TL;DR: Granite 4.2 is our first family of dense, decoder-only reasoning LLMs, released in three sizes: 3B, 8B, and 30B. These models are post-trained from Granite-4.1 base models. Granite-4.1 base models were pre-trained from scratch on roughly 15T tokens with a five-phase strategy that extends the context window to 512K tokens, supervised fine-tuned on chain-of-thought, reasoning, and agentic-trajectory data, then post-trained with a multi-stage reinforcement...

## Making LLMs faster without sacrificing accuracy

DevFeed: [Making LLMs faster without sacrificing accuracy](<https://devfeed.tech/articles/making-llms-faster-without-sacrificing-accuracy-7603.md>)

Original publisher: [Read original article](<https://www.amazon.science/blog/making-llms-faster-without-sacrificing-accuracy>)

Author: Tao Yu; Youngsuk Park

Published: 2026-05-15T13:00:00Z

Content type: article

Language: en

Sources: [Amazon Science homepage](<https://devfeed.tech/sources/amazon-science-homepage.md>)

Topics: [Language models](<https://devfeed.tech/topics/language-models.md>), [Training AI Models](<https://devfeed.tech/topics/training-ai-models.md>), [web applications](<https://devfeed.tech/topics/web-applications.md>)

Tags: [architecture](<https://devfeed.tech/tags/architecture.md>), [chinchilla-scaling-law](<https://devfeed.tech/tags/chinchilla-scaling-law.md>), [conversational-ai](<https://devfeed.tech/tags/conversational-ai.md>), [generative-ai](<https://devfeed.tech/tags/generative-ai.md>), [grouped-query-attention](<https://devfeed.tech/tags/grouped-query-attention.md>), [hyperparameter-optimization](<https://devfeed.tech/tags/hyperparameter-optimization.md>), [iclr-2026](<https://devfeed.tech/tags/iclr-2026.md>), [inference](<https://devfeed.tech/tags/inference.md>), [inference-efficiency](<https://devfeed.tech/tags/inference-efficiency.md>), [large-language-models](<https://devfeed.tech/tags/large-language-models.md>), [large-language-models-llms](<https://devfeed.tech/tags/large-language-models-llms.md>), [llm-optimization](<https://devfeed.tech/tags/llm-optimization.md>), [llms](<https://devfeed.tech/tags/llms.md>), [machine-learning](<https://devfeed.tech/tags/machine-learning.md>), [model-architecture](<https://devfeed.tech/tags/model-architecture.md>), [network-architectures](<https://devfeed.tech/tags/network-architectures.md>), [scaling-laws](<https://devfeed.tech/tags/scaling-laws.md>), [training](<https://devfeed.tech/tags/training.md>), [transformer-architecture](<https://devfeed.tech/tags/transformer-architecture.md>)

### AI overview

The article presents scaling laws that connect LLM architectural choices to the tradeoff between accuracy and efficiency. It describes how these choices can improve inference throughput without reducing accuracy.

### Source excerpt

A new scaling law that relates particular architectural choices to loss helps identify models that improve throughput by up to 47% with no loss of accuracy.

## SmolLM3: smol, multilingual, long-context reasoner

DevFeed: [SmolLM3: smol, multilingual, long-context reasoner](<https://devfeed.tech/articles/smollm3-smol-multilingual-long-context-reasoner-7482.md>)

Original publisher: [Read original article](<https://huggingface.co/blog/smollm3>)

Author: Elie Bakouch; Carlos Miguel Patiño; Anton Lozhkov; Edward Beeching; Aymeric Roucher; Nouamane Tazi; Aksel Joonas Reedi; Guilherme Penedo; Hynek Kydlicek; Clémentine Fourrier

Published: 2025-07-08T00:00:00Z

Content type: article

Language: en

Sources: [Hugging Face - Blog](<https://devfeed.tech/sources/hugging-face-blog.md>)

Topics: [AI Chat](<https://devfeed.tech/topics/ai-chat.md>)

Tags: [architecture](<https://devfeed.tech/tags/architecture.md>), [artificial-intelligence](<https://devfeed.tech/tags/artificial-intelligence.md>), [community](<https://devfeed.tech/tags/community.md>), [datasets](<https://devfeed.tech/tags/datasets.md>), [grouped-query-attention](<https://devfeed.tech/tags/grouped-query-attention.md>), [inference](<https://devfeed.tech/tags/inference.md>), [llama](<https://devfeed.tech/tags/llama.md>), [llm](<https://devfeed.tech/tags/llm.md>), [long-context](<https://devfeed.tech/tags/long-context.md>), [models](<https://devfeed.tech/tags/models.md>), [nlp](<https://devfeed.tech/tags/nlp.md>), [open-source](<https://devfeed.tech/tags/open-source.md>), [performance](<https://devfeed.tech/tags/performance.md>), [reasoning](<https://devfeed.tech/tags/reasoning.md>), [research](<https://devfeed.tech/tags/research.md>), [training](<https://devfeed.tech/tags/training.md>)

### AI overview

SmolLM3 is a 3B multilingual, long-context reasoning model. The article shares its training recipe and describes architecture changes including grouped-query attention, NoPE, and intra-document masking.

### Source excerpt

We're on a journey to advance and democratize artificial intelligence through open source and open science.