AI-Hypercomputer/JetStream
View on GitHubJetStream is a throughput and memory optimized engine for LLM inference on XLA devices, starting with TPUs (and GPUs in future -- PRs welcome).
- Stars
- 457
- Forks
- 67
- Open beginner issues
- 0
- Indexed issues
- 14
- Dominant language
- Python
- License
- Apache-2.0
- Last GitHub push
- Jan 5, 2026
- Latest indexed
- Sep 13, 2026
- Contributing guide
- Contributing guide
- Code of conduct
- No code of conduct
- Beginner labels
- No beginner labels indexed
- PR merge metrics
- No merged PRs in 30d
-
AI-Hypercomputer/JetStream#45 · 1 comment · 0 reactions · 1 assignee ·
-
AI-Hypercomputer/JetStream#61 · 2 comments · 0 reactions · 1 assignee ·
-
AI-Hypercomputer/JetStream#88 · 0 comments · 0 reactions · 0 assignees ·
-
when to support gpu? Open
AI-Hypercomputer/JetStream#120 · 2 comments · 0 reactions · 1 assignee ·
-
AI-Hypercomputer/JetStream#131 · 2 comments · 0 reactions · 1 assignee ·
-
AI-Hypercomputer/JetStream#135 · 0 comments · 0 reactions · 1 assignee ·
-
AI-Hypercomputer/JetStream#137 · 0 comments · 0 reactions · 1 assignee ·
-
AI-Hypercomputer/JetStream#140 · 2 comments · 0 reactions · 1 assignee ·
-
AI-Hypercomputer/JetStream#143 · 0 comments · 0 reactions · 1 assignee ·
-
AI-Hypercomputer/JetStream#146 · 1 comment · 0 reactions · 1 assignee ·
-
AI-Hypercomputer/JetStream#153 · 0 comments · 0 reactions · 0 assignees ·
-
AI-Hypercomputer/JetStream#241 · 0 comments · 0 reactions · 0 assignees ·
-
AI-Hypercomputer/JetStream#276 · 1 comment · 0 reactions · 0 assignees ·
-
MOE with JetStream Open
AI-Hypercomputer/JetStream#277 · 0 comments · 0 reactions · 0 assignees ·