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 issues indexadas) (0 good first issues abertas)
Repositórios
Repositórios de AI-Hypercomputer
AI-Hypercomputer/maxtextPython
A simple, performant, and scalable Jax LLM!
(2.398 stars) (589 forks) (1 issue indexada) (1 good first issue aberta)
(121 stars) (75 forks) (0 issues indexadas) (0 good first issues abertas)