Extension index for stable-diffusion-webui
FlashMLA: Efficient Multi-head Latent Attention Kernels
A Family of Open Foundation Models for Code Intelligence
MiniMax M2.1, a SOTA model for real-world dev & agents.
Open-weight, large-scale hybrid-attention reasoning model
Qwen2.5-Coder is the code version of Qwen2.5, the large language model
Lightweight 24B agentic coding model with vision and long context
Agentic 123B coding model optimized for large-scale engineering
Kimi K2: 1T-param MoE model for advanced coding and agentic reasoning