flops

Sep 10, 2026

• attention
• multi-head-attention
• transformer-block
• pre-ln
• post-ln
• layernorm
• ffn
• gelu
• flops
• scaling-laws

Sep 10, 2026

• attention
• transformers
• sparse-attention
• sliding-window
• longformer
• bigbird
• attention-sinks
• streaming
• long-context
• flops

Sep 02, 2026

• gpu
• arithmetic-intensity
• roofline
• flops
• bandwidth
• memory-bound
• compute-bound
• llm-systems