aleph-alpha-inference
Aleph Alpha's Apache 2.0 vLLM plugin and container for serving Kolibri models.
0 members list aleph-alpha-inference, unchanged over the last 12 weeks, data as of 21 November 2026
Members who list aleph-alpha-inference in their Stack, by week.
Members who list aleph-alpha-inference
Be the first to add aleph-alpha-inference
Nobody on Stackness runs aleph-alpha-inference yet. Add it to your stack and you're the first member running it.
About aleph-alpha-inference
Aleph Alpha Inference is a plugin and container for serving Kolibri models, which are large language models. It builds on vLLM, a framework for serving and running inference on large language models. The tool enables developers to deploy and run Kolibri models in their applications and infrastructure. Aleph Alpha Inference is developed by Aleph-Alpha and released under the Apache 2.0 license, making it freely available for both open source and commercial use.
The tool is written in Python and designed to integrate with existing vLLM deployments. It provides a containerized approach to model serving, allowing developers to package and distribute Kolibri models alongside the inference runtime. This makes it suitable for scenarios where developers need to serve language models in production environments or integrate them into larger systems.
Checked 17 November 2026.
Nobody on Stackness runs aleph-alpha-inference yet.
Sign up and add itPosts about aleph-alpha-inference
- Mistral Large 4 vs Beam vs Kolibri: which open weights you can download, and what your hardware can serve
Only Kolibri's weights are out. Beam and Mistral Large 4 stay API previews until late October, and Kolibri's 4-bit build runs at 50 tok/s on a 64GB Mac.