BitDistill:LLM权重从FP16量化到1.58-bit,精度基本无损,内存消耗下降显著,推理速度提升
论文BitNet Distillation提出 BitNet Distillation(BitDistill) […]
BitDistill:LLM权重从FP16量化到1.58-bit,精度基本无损,内存消耗下降显著,推理速度提升 Read More »
论文BitNet Distillation提出 BitNet Distillation(BitDistill) […]
BitDistill:LLM权重从FP16量化到1.58-bit,精度基本无损,内存消耗下降显著,推理速度提升 Read More »
经典CFD(Computational Fluid Dynamics)仿真在汽车与航空航天外流场分析中耗时高、
AB-UPT(Anchored-Branched Universal Physics Transformer):具备较高准确性和效率的CFD建模替代 Read More »
扩散模型在图像生成上长期以卷积式 U-Net 为主干,但论文Scalable Diffusion Models
Diffusion Transformer (DiT) Read More »
论文In-Context Fine-Tuning for Time-Series Foundation Mod
用“上下文内微调(In-Context Fine-Tuning, ICF)”方法改进TimesFM(跨领域零样本预测的时序基础模型) Read More »
论文Geometry Aware Operator Transformer As An Efficient A
创新的神经算子(neural operator)架构:GAOT(Geometry Aware Operator Transformer) Read More »