标签: LLM
所有带有此标签的文章 "LLM".
-
Titans: Learning to Memorize at Test Time
更新于:从TTT改进而来的新架构,尝试通过TTT的方式改进模型的记忆能力。
-
Were RNNs All We Needed?
更新于:改进RNN,便于scale up
-
I-LLM: Efficient Integer-Only Inference for Fully-Quantized Low-Bit Large Language Models
更新于:LLM的Interger-Only PTQ量化工作。
-
FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness
更新于:Flash Attention,利用硬件结构加速Attention计算速度、减少内存占用的算法。核心是Tiling,Online Softmax和Kernel Fusion。
-
PowerInfer: Fast Large Language Model Serving with a Consumer-grade GPU
更新于:From IPADS, 利用模型预测LLM中需要激活的MoE or Neuron,减少资源消耗。