LLM inference
2 published articles
LLMs & Models3 min read
Systems optimization
DSpark shows why fast AI inference is a scheduling problem, not a model trick
DeepSeek's DSpark paper reveals that naive speculative decoding degrades throughput under high concurrency. Its solution, confidence-scheduled verification, adapts block length per request and shifts the Pareto frontier of serving performance.
2026-07-12
DeepSeek2 min read
LLM Inference Optimization
Aleph Alpha builds a theoretical inference model to decode DeepSeek V3 performance from hardware primitives
Aleph Alpha's theoretical model predicts DeepSeek V3 inference performance from hardware parameters alone, revealing how GPU count and interconnect bandwidth shift the bottleneck between compute, memory, and communication.
2026-07-04