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).

Date Created 2024-03-01 (9 months ago)

Commits 126 (last one 3 days ago)

Stargazers 256 (3 this week)

Watchers 19 (0 this week)

Forks 32

License apache-2.0

Ranking

RepositoryStats indexes 595,856 repositories, of these AI-Hypercomputer/JetStream is ranked #151,483 (75th percentile) for total stargazers, and #117,069 for total watchers. Github reports the primary language for this repository as Python, for repositories using this language it is ranked #26,496/119,431.

AI-Hypercomputer/JetStream is also tagged with popular topics, for these it's ranked: pytorch (#2,148/6025), llm (#1,045/2913), gpt (#407/1146), large-language-models (#416/1090), transformer (#363/1018), gpu (#363/918), llama (#247/547), mlops (#162/421), inference (#132/309), llama2 (#91/238), llmops (#97/171), llm-inference (#58/171)

Other Information

AI-Hypercomputer/JetStream has 6 open pull requests on Github, 115 pull requests have been merged over the lifetime of the repository.

Github issues are enabled, there are 11 open issues and 16 closed issues.

There have been 4 releases, the latest one was published on 2024-12-18 (3 days ago) with the name v0.3.

All Topics

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

Star History

Github stargazers over time

Watcher History

Github watchers over time, collection started in '23

Recent Commit History

126 commits on the default branch (main) since jan '22

Yearly Commits

Commits to the default branch (main) per year

Issue History

Languages

The primary language is Python but there's also others...

updated: 2024-12-19 @ 05:11am, id: 765455287 / R_kgDOLZ_rtw