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 indexierte Issues) (0 offene good first issues)
Repositories
AI-Hypercomputer Repositories
AI-Hypercomputer/maxtextPython
A simple, performant, and scalable Jax LLM!
(2.398 Stars) (589 Forks) (1 indexiertes Issue) (1 offenes good first issue)
(121 Stars) (75 Forks) (0 indexierte Issues) (0 offene good first issues)