The Structure of LLM Inference Revolutions
October 22, 2026
TL;DR: LLM inference is undergoing a paradigm shift from batch parallelism to sequence parallelism.
Posts by Tags
language models
The Parallel Decoding Trilemma
November 25, 2025
TL;DR: Parallel decoding is a fight to increase speed while maintaining fluency and diversity.
machine learning
The Structure of LLM Inference Revolutions
October 22, 2026
TL;DR: LLM inference is undergoing a paradigm shift from batch parallelism to sequence parallelism.
The Parallel Decoding Trilemma
November 25, 2025
TL;DR: Parallel decoding is a fight to increase speed while maintaining fluency and diversity.
parallel decoding
The Structure of LLM Inference Revolutions
October 22, 2026
TL;DR: LLM inference is undergoing a paradigm shift from batch parallelism to sequence parallelism.
The Parallel Decoding Trilemma
November 25, 2025
TL;DR: Parallel decoding is a fight to increase speed while maintaining fluency and diversity.