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).
Why this job: topics: llm-inference, inference, model-serving, llama, llm inference
What it does
JetStream is a throughput and memory optimized engine for LLM inference on XLA devices, starting with TPUs (and GPUs in future -- PRs welcome).
Get started
No single install command. Read the steps in the README (opens in new tab)
- Maintenance
- Inactive
- Last commit 10 months ago
- Stars
- 473
- On GitHub
- Licence
- Apache-2.0
- Allows business use
- Downloads for
- None listed
- No release files
- Latest version
- v0.3
- Released 23 months ago
- Built with
- Python
- 94% of the code
Is it looked after?
- Contributors
- Not stated
- Last 90 days
- Issues
- 52% closed
- 15 still open
- Pull requests
- 209 merged
- 12 waiting
- Releases
- 4
- 0 in the last year
- Contributing guide (opens in new tab)
- No security policy
- No code of conduct
Similar repos
| Repo | Stars | Last commit | Licence | Downloads for |
|---|---|---|---|---|
| vllm-project / vllm | 96,774 | today | Apache-2.0 | Mac, Linux |
| alibaba / rtp-llm | 1,394 | yesterday | Apache-2.0 | No downloads |
| zhihu / ZhiLight | 906 | 7 months ago | Apache-2.0 | No downloads |
More: languages, topics and project record
Languages
- Python 94%
- Shell 6%
- Dockerfile <1%
- Makefile <1%
Topics
- gemma
- gpt
- gpu
- inference
- jax
- large-language-models
- llama
- llama2
- llm
- llm-inference
- llmops
- mlops
Project record
- JobLocal LLMs
- StatusListed
- Commits258
- Forks70
- Watching22
- Stars in 28 days+3
- CreatedMar 1, 2024
- First seen by usNov 7, 2026
- CheckedNov 8, 2026