Memory Bandwidth
نطاق الذاكرة
السرعة القصوى التي يمكن بها نقل البيانات بين الذاكرة ووحدات المعالجة، وتُقاس عادةً بالتيرابايت في الثانية.
The maximum rate at which data can be transferred between memory and processing units, typically measured in terabytes per second.
Also translated asعرض حزمة الذاكرة، معدل نقل البيانات
First appears in this corpus in: ZeRO: Memory Optimizations Toward Training Trillion Parameter Models (2019)
Appears in these papers
- FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness2022in the sky ✦
- GPTQ: Accurate Post-Training Quantization for Generative Pre-Trained Transformers2022in the sky ✦
- GQA: Training Generalized Multi-Query Transformer Models from Multi-Head Checkpoints2023in the sky ✦
- GQA: Training Generalized Multi-Query Transformer Models from Multi-Head Checkpoints2023in the sky ✦
- Mistral 7B2023in the sky ✦
- Fast Inference from Transformers via Speculative Decoding2023in the sky ✦
- ZeRO: Memory Optimizations Toward Training Trillion Parameter Models2019in the sky ✦