Skip to content
conftrace_

megatron-lm

1 paper

Explore in graph

Co-occurring keywords · papers mentioning both

3d parallelism (1) kv caching (1) pipeline parallelism (1) early exit (1) autoregressive generation (1)

Papers

EE-LLM: Large-Scale Training and Inference of Early-Exit Large Language Models with 3D Parallelism ICML 2024