AI Architecture & Systems
1
Microarchitecture
2
Kernel
3
Compiler
4
Architecture
5
System
6
Algorithms
Algorithms
/
§6.30
Model Family: DeepSeek
6.30.1
DeepSeek LLM and DeepSeekMoE
#
6.30.2
DeepSeek-V2: MLA and Fine-Grained MoE
#
6.30.3
DeepSeek-V3: Low-Precision Training, Load Balancing, and MTP
#
6.30.4
DeepSeek-R1: Reasoning RL and Distillation
#
6.30.5
DeepSeek-V3.1/V3.2: Reasoning Modes and Sparse Attention
#
6.30.6
DeepSeek-V4: Public Model Report and Deployment Requirements
#
6.30.7
Model–Kernel–System Co-Design Across the DeepSeek Family
#
← Previous
6.29 Model Family: Mistral and Mixtral
→ Next
6.31 Model Family: Qwen