01
Kimi K3：架构、训练与推理系统研究
ai-systems / llm-inference
llm-inferenceattentionmoedistributed-training
+1
02
Token Flow 与 Hidden State：从 Attention 到 LM Head
ai-systems / llm-inference
llm-inferencetransformerhidden-stateattention
+2
03
Attention 架构演化：从多头注意力（MHA）到 GQA、MLA
ai-systems / llm-inference
llm-inferenceattentionkv-cache
04
DeepSeek MLA：低秩 KV Cache 与推理效率
ai-systems / llm-inference
llm-inferenceattentionkv-cachedeepseek
+1
05
Chunked Prefill 深入分析：调度、Chunk Size 与 Attention 形状
ai-systems / llm-inference
llm-inferencechunked-prefillschedulingprefill
+3
06
Causal Attention：为什么 KV hit 后 Attention 按 1 - h² 缩放
ai-systems / llm-inference
llm-inferenceattentionkv-cachesimulator
+1
07
CSA/HCA 注意力：DeepSeek-V4 的混合压缩稀疏机制
ai-systems / llm-inference
attentionsparse-attentionkv-cachedeepseek