JetStream is a throughput and memory optimized engine for LLM inference on XLA devices, starting with TPUs (and GPUs in future -- PRs welcome).
(451 stars) (67 forks) (0 件の索引済み issue) (0 件のオープンな good first issue)
リポジトリ
AI-Hypercomputer のリポジトリ
AI-Hypercomputer/maxtextPython
A simple, performant, and scalable Jax LLM!
(2,398 stars) (589 forks) (1 件の索引済み issue) (1 件のオープンな good first issue)
(121 stars) (75 forks) (0 件の索引済み issue) (0 件のオープンな good first issue)