GitHub / AI-Hypercomputer / JetStream

JetStream is a throughput and memory optimized engine for LLM inference on XLA devices, starting with TPUs (and GPUs in future -- PRs welcome).

JSON API: http://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/AI-Hypercomputer%2FJetStream

Commit Stats

Commits: 121
Authors: 21
Mean commits per author: 5.76
Development Distribution Score: 0.645
More commit stats: https://commits.ecosyste.ms/hosts/GitHub/repositories/AI-Hypercomputer/JetStream

Topics: gemma, gpt, gpu, inference, jax, large-language-models, llama, llama2, llm, llm-inference, llmops, mlops, model-serving, pytorch, tpu, transformer

• Files
• Readme
• Dependencies