Search: github.com/kmoe | Heykuki News

Heykuki News

Top New Best Ask Show Jobs

Top New Best Ask Show Jobs

181.

Moe-LLaVA: Mixture of Experts for Large Vision-Language Models (github.com/PKU-YuanGroup)

2 points

2 years ago

182.

Hydra – Model of Experts (github.com/SkunkworksAI)

2 points

3 years ago

183.

Pruning GPT-OSS 4.8B to 20B (232 models) (github.com/AmanPriyanshu)

3 points

10 months ago

184.

Rails MVC VS Sproutcore MVC (gmoeck.github.com)

44 points

15 years ago

185.

Show HN: A different interface for reading Hacker News (moeffju.github.com)

36 points

15 years ago

186.

Don't Make Your Code "More Testable" (gmoeck.github.com)

4 points

14 years ago

187.

Why you should care about encapsulation (gmoeck.github.com)

1 point

15 years ago

188.

Löb and möb: strange loops in Haskell (2015) (github.com/quchen)

153 points

3 years ago

189.

Löb and Möb: Loops in Haskell (2013) (github.com/quchen)

91 points

7 months ago

190.

Löb and möb: strange loops in Haskell (2013) (github.com/quchen)

86 points

8 years ago

191.

Löb and möb: strange loops in Haskell (github.com/quchen)

4 points

13 years ago

192.

Löb and möb: strange loops in Haskell (github.com/quchen)

4 points

4 years ago

193.

Löb and möb: strange loops in Haskell (github.com/quchen)

2 points

11 years ago

194.

DeepSeek open source DeepEP – library for MoE training and Inference (github.com/deepseek-ai)

536 points

a year ago

195.

Kimi K2 is a state-of-the-art mixture-of-experts (MoE) language model (github.com/MoonshotAI)

352 points

ConteMascetti71

a year ago

196.

Kimi K2 is a state-of-the-art mixture-of-experts (MoE) language model (twitter.com)

348 points

a year ago

197.

LPLB: An early research stage MoE load balancer based on linear programming (github.com/deepseek-ai)

43 points

7 months ago

198.

DeepSeek-VL2: MoE Vision-Language Models for Advanced Multimodal Understanding (github.com/deepseek-ai)

36 points

a year ago

199.

DeepSeek-V2: A Strong, Economical, and Efficient Moe Language Model (github.com/deepseek-ai)

14 points

2 years ago

200.

A Library to build MoE from HF models

9 points

2 years ago

201.

Show HN: Phase Router – capacity-aware routing for MoE (github.com/TSltd)

5 points

a month ago

202.

LongCat-Flash, a language model with 560B total parameters, MoE architecture (github.com/meituan-longcat)

4 points

9 months ago

203.

HuggingFace: Support for the Mixtral Moe (github.com/huggingface)

4 points

2 years ago

204.

Slicing an 80B MoE LLM into 40B domain specialists (github.com/JThomas-CoE)

3 points

3 months ago

205.

Show HN: A 6.9B Moe LLM in Rust, Go, and Python (github.com/fumi-engineer)

3 points

5 months ago

206.

Shimmy v1.7.0: Running 42B Moe Models on Consumer GPUs with 99.9% VRAM Reduction (github.com/Michael-A-Kuykendall)

3 points

8 months ago

207.

Huawei's Pangu Pro MoE model is likely derived from Qwen model (github.com/HonestAGI)

3 points

a year ago

208.

Show HN: Modernizing my old PhD work in an evening with little Qwen3.6 MoE (github.com/verdverm)

3 points

16 days ago

209.

QMoE Support for Mixtral (github.com/ggerganov)

3 points

2 years ago

210.

OpenMoE – A family of open-sourced Mixture-of-Experts (MoE) LLMs (github.com/XueFuzhao)

3 points

3 years ago