Hackernews posts about Kimi Linear

RSS feed for Kimi Linear

01
newKimi Linear: An Expressive, Efficient Attention Architecture (2025)arxiv.org
▲ 306ronfriedhaber 102d 💬 133
02
newKimi Linear: An Expressive, Efficient Attention Architecturegithub.com
▲ 217blackcat201 372d 💬 47
03
newKimi Linear: An Expressive, Efficient Attention Architecturearxiv.org
▲ 6birriel 369d discuss
04
newSelf-Hosted LLM Upgrade on AMD: Kimi Linear 48B, Qwen3 Coder Next, and Q2_K_XLsite.bhamm-lab.com
▲ 4bhamm-lab 261d 💬 1
05
newKimi Linear: An Expressive, Efficient Attention Architecturearxiv.org
▲ 3ashish01 109d discuss
06
newExplanation of Gated DeltaNet (Qwen3-Next and Kimi Linear)github.com
▲ 3ModelForge 368d discuss
07
newMoonshotAI Kimi-Lineargithub.com
▲ 2vinhnx 372d discuss
08
newKimi Linear: An Expressive, Efficient Attention Architecturearxiviq.substack.com
▲ 1che_shr_cat 370d discuss
09
newShow HN: A new engine to run Kimi K3 on a laptop
▲ 7marcobambini 100d 💬 3
10
newShow HN: OS Megakernel that match M5 Max Tok/w at 2x the Throughput on RTX 3090github.com
▲ 6GreenGames 212d 💬 1
11
newGuide to the Kimi DeltaNet Family of linear attentionblog.doubleword.ai
▲ 3kkm 102d discuss
12
newA walk through of the DeltaNet family of linear attention variantsblog.doubleword.ai
▲ 297AnhTho_FR 101d 💬 126
13
newShow HN: Ardent, a code-first agent for non-engineering workardent.ai
▲ 10nkohari 64d 💬 2
14
newShow HN: Kimu – Open-Source Video Editorwww.trykimu.com
▲ 106robinroy03 459d 💬 35
15
newShow HN: Turn Git commits into Linear-style release notewww.updated.dev
▲ 2hyun_kim 331d 💬 2
16
newShow HN: Distilling DeepSeek into GPT-OSS doesn't transfer censorship. Try itwww.ctgt.ai
▲ 170cgorlla 99d 💬 73