DEV Community

#moe

Posts

👋 Sign in for the ability to sort posts by relevant, latest, or top.
Hugging Face’s 70k-Word MoE Handbook After 800k GPU Hours — Why Sparsity Still Wins for Local Real-Time Tools
madnessbrains_i profile
devs

Hugging Face’s 70k-Word MoE Handbook After 800k GPU Hours — Why Sparsity Still Wins for Local Real-Time Tools

#moe #inference #localai #windows
Comments
4 min read
Inkling 2 Small 发布：68 小时主预训练，多模态与可定制性并重
arthur1988 profile
arthur

Inkling 2 Small 发布：68 小时主预训练，多模态与可定制性并重

#moe
Comments
1 min read
Running MoE LLMs Larger Than Your RAM: A Practical Guide to mmap, Expert Offloading and SSD Streaming with llama.cpp
eme_gug_0821b41b948be6516 profile

Running MoE LLMs Larger Than Your RAM: A Practical Guide to mmap, Expert Offloading and SSD Streaming with llama.cpp

#llm #llamacpp #moe #performance
Comments
8 min read
An 80GB H100, and only 3B of the model could keep up with conversation
orca_forge profile

An 80GB H100, and only 3B of the model could keep up with conversation

#gpu #llm #moe #ai
Comments
5 min read
The great sparsification: 2026 open-weight MoE models now activate 1 to 9 percent of their weights
ai_maya_063fc568e157562fd profile

The great sparsification: 2026 open-weight MoE models now activate 1 to 9 percent of their weights

#ai #machinelearning #llm #moe
Comments
6 min read
DeepSeek R1: The Open-Source Reasoning Revolution That Changes Everything
ryan_zhao profile

DeepSeek R1: The Open-Source Reasoning Revolution That Changes Everything

#ai #deepseek #moe #reasoning
Comments
2 min read
👋 Sign in for the ability to sort posts by relevant, latest, or top.