Search: github.com/kmoe | Heykuki News

HK

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 years ago

2 points

182.

Hydra – Model of Experts

github.com/SkunkworksAI

3 years ago

2 points

183.

Pruning GPT-OSS 4.8B to 20B (232 models)

github.com/AmanPriyanshu

10 months ago

3 points

184.

Rails MVC VS Sproutcore MVC

gmoeck.github.com

15 years ago

44 points

185.

Show HN: A different interface for reading Hacker News

moeffju.github.com

15 years ago

36 points

186.

Don't Make Your Code "More Testable"

gmoeck.github.com

14 years ago

4 points

187.

Why you should care about encapsulation

gmoeck.github.com

15 years ago

1 points

188.

Löb and möb: strange loops in Haskell (2015)

github.com/quchen

3 years ago

153 points

189.

Löb and Möb: Loops in Haskell (2013)

github.com/quchen

8 months ago

91 points

190.

Löb and möb: strange loops in Haskell (2013)

github.com/quchen

8 years ago

86 points

191.

Löb and möb: strange loops in Haskell

github.com/quchen

13 years ago

4 points

192.

Löb and möb: strange loops in Haskell

github.com/quchen

4 years ago

4 points

193.

Löb and möb: strange loops in Haskell

github.com/quchen

11 years ago

2 points

194.

DeepSeek open source DeepEP – library for MoE training and Inference

github.com/deepseek-ai

a year ago

536 points

195.

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

github.com/MoonshotAI

a year ago

ConteMascetti71

352 points

196.

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

a year ago

348 points

197.

LPLB: An early research stage MoE load balancer based on linear programming

github.com/deepseek-ai

7 months ago

43 points

198.

DeepSeek-VL2: MoE Vision-Language Models for Advanced Multimodal Understanding

github.com/deepseek-ai

a year ago

36 points

199.

DeepSeek-V2: A Strong, Economical, and Efficient Moe Language Model

github.com/deepseek-ai

2 years ago

14 points

200.

A Library to build MoE from HF models

2 years ago

9 points

201.

Show HN: Phase Router – capacity-aware routing for MoE

github.com/TSltd

2 months ago

5 points

202.

Running a 35B MoE model on a 2017 AMD RX 580 8GB via Vulkan (no ROCm/CUDA)

github.com/aivisionslab-studios

2 days ago

4 points

203.

LongCat-Flash, a language model with 560B total parameters, MoE architecture

github.com/meituan-longcat

10 months ago

4 points

204.

HuggingFace: Support for the Mixtral Moe

github.com/huggingface

3 years ago

4 points

205.

Slicing an 80B MoE LLM into 40B domain specialists

github.com/JThomas-CoE

3 months ago

3 points

206.

Show HN: A 6.9B Moe LLM in Rust, Go, and Python

github.com/fumi-engineer

5 months ago

3 points

207.

Shimmy v1.7.0: Running 42B Moe Models on Consumer GPUs with 99.9% VRAM Reduction

github.com/Michael-A-Kuykendall

8 months ago

3 points

208.

Huawei's Pangu Pro MoE model is likely derived from Qwen model

github.com/HonestAGI

a year ago

3 points

209.

Show HN: Modernizing my old PhD work in an evening with little Qwen3.6 MoE

github.com/verdverm

a month ago

3 points

210.

QMoE Support for Mixtral

github.com/ggerganov

3 years ago

3 points