Scaling Laws Meet Model Architecture: Toward Inference-Efficient LLMs
"架构优化" 相关文章
Scaling Laws Meet Model Architecture: Toward Inference-Efficient LLMs
[职场话题] 领导让我降本增效，怎么搞
ShishuLM: Lightweight Language Model with Hybrid Decoder-MLP Architecture and Paired Weight Sharing
从GPT-1到GPT-2的性能飞跃及其驱动因素分析
从GPT-1到GPT-2的性能飞跃及其驱动因素分析
[程序员] 高并发架构求解：千万级在线长连接，有偿咨询（杭州）
【信创-k8s】海光/兆芯+银河麒麟 V10 离线部署 k8s1.31.8+kubesphere4.1.3
Patent Language Model Pretraining with ModernBERT
ASNN: Learning to Suggest Neural Architectures from Performance Distributions
On the Limits of Hierarchically Embedded Logic in Classical Neural Networks
Milvus Week｜开源，Milvus 2.6功能预览：内存减少 72%，速度比ES快4倍
得物自研DGraph4.0推荐核心引擎升级之路
得物商家客服从Electron迁移到Tauri的技术实践
How Facteus improved Quantamatics performance by adopting Amazon Aurora Serverless and Amazon EKS
Nvidia AI Releases Llama-3.1-Nemotron-51B: A New LLM that Enables Running 4x Larger Workloads on a Single GPU During Inference
