alibaba / rtp-llm
RTP-LLM: Alibaba's high-performance LLM inference engine for diverse applications.
Why this job: says: inference engine, llm inference; topics: inference, llm-serving, model-serving, llama
What it does
- Alibaba's international AI platform, Aidge
- OpenSearch LLM Smart Q&A Edition
- Large Language Model based Long-tail Query Rewriting in Taobao Search
- Utilizes high-performance CUDA kernels, including PagedAttention, FlashAttention, FlashDecoding, etc.
Get started
No single install command. Read the steps in the README (opens in new tab)
- Maintenance
- Active
- Last commit today
- Stars
- 1,394
- +7 this week
- Licence
- Apache-2.0
- Allows business use
- Downloads for
- None listed
- No release files
- Latest version
- v0.2.0
- Released 12 months ago
- Built with
- Python
- 44% of the code
Is it looked after?
- Contributors
- 27
- Last 90 days
- Issues
- 68% closed
- 41 still open
- Pull requests
- 755 merged
- 252 waiting
- Releases
- 15
- 0 in the last year
- No contributing guide
- No security policy
- No code of conduct
Similar repos
| Repo | Stars | Last commit | Licence | Downloads for |
|---|---|---|---|---|
| vllm-project / vllm | 96,588 | today | Apache-2.0 | Mac, Linux |
| liguodongiot / llm-action | 25,266 | 26 days ago | Apache-2.0 | No downloads |
| thu-pacman / chitu | 3,000 | 2 days ago | Apache-2.0 | No downloads |
More: languages, topics and project record
Languages
- Python 44%
- Cuda 27%
- C++ 14%
- Java 12%
Topics
- gpt
- inference
- llama
- llm
- llm-serving
- llmops
- model-serving
Project record
- JobLocal LLMs
- StatusListed
- Commits4,877
- Forks300
- Watching18
- Stars in 28 days+34
- CreatedDec 27, 2023
- First seen by usNov 7, 2026
- CheckedNov 9, 2026