aleph-alpha-inference
A vLLM plugin that serves Aleph Alpha models. It adds:
| Model | Architecture | Reasoning parser | Tool call parser |
|---|---|---|---|
| Kolibri 1 | Kolibri1ForCausalLM |
kolibri1 |
kolibri1 |
vLLM finds the plugin through its vllm.general_plugins entry point, so
installing the package is all the setup there is.
Install
Each release supports one vLLM minor version, currently vLLM 0.29.
pip install aleph-alpha-inference
This installs the supported vLLM as well. To add the plugin to an existing
vLLM 0.29 installation, such as the vllm/vllm-openai:v0.29.0 image, without
touching its vLLM, torch or transformers:
pip install --no-deps aleph-alpha-inference
Serve
vllm serve Aleph-Alpha/Kolibri-1 \
--kv-cache-dtype fp8 \
--reasoning-parser kolibri1 \
--tool-call-parser kolibri1 \
--enable-auto-tool-choice
For the BF16 weights, serve Aleph-Alpha/Kolibri-1-BF16 and drop
--kv-cache-dtype fp8.
Thinking is on by default. Turn it off for a request with
reasoning_effort: "none" or enable_thinking: false:
curl http://localhost:8000/v1/chat/completions \
-H "Content-Type: application/json" \
-d '{
"model": "Aleph-Alpha/Kolibri-1",
"messages": [{"role": "user", "content": "What is the capital of France?"}],
"chat_template_kwargs": {"enable_thinking": false}
}'
The kolibri1 reasoning parser reads the same switch as the chat template,
so the response's reasoning and content are split correctly whichever way
thinking is set.
Development
uv run pytest -m "not gpu" # runs anywhere
uv run pytest -m gpu # needs a CUDA GPU supported by vLLM
License
Metadata
Release files for aleph-alpha-inference 1.0.0
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| aleph_alpha_inference-1.0.0.tar.gz | 18.1 kB | Without provenance | Details for aleph_alpha_inference-1.0.0.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| aleph_alpha_inference-1.0.0-py3-none-any.whl | Python 3 | none | any | Details for aleph_alpha_inference-1.0.0-py3-none-any.whl |
Total release size: 31.5 kB
Release files / aleph_alpha_inference-1.0.0.tar.gz
| Download URL | aleph_alpha_inference-1.0.0.tar.gz |
|---|---|
| Size | 18.1 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
b45baaf3f9769bffb5bfcf65b057a1768501df0306a67e957c41ee6915152e01
|
|
BLAKE2b-256 checksum How to use checksums |
b7f7ada2bb57b21f88222bb68dafb12ab873c0dbe64740b84cd470637a6bd1b1
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
uv/0.12.22 {"installer":{"name":"uv","version":"0.12.22","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Ubuntu","version":"24.04","id":"noble","libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":true}
|
Release files / aleph_alpha_inference-1.0.0-py3-none-any.whl
| Download URL | aleph_alpha_inference-1.0.0-py3-none-any.whl |
|---|---|
| Size | 13.4 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
5a0ca118e67924f10c4f9c04dd64bef117007a17dd820233a8841b9cb8d6f211
|
|
BLAKE2b-256 checksum How to use checksums |
b0d71eda35b6ee0293f2a52d7a653cf5a4d54c93f21e2e359fe70a7e7b87a851
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
uv/0.12.22 {"installer":{"name":"uv","version":"0.12.22","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Ubuntu","version":"24.04","id":"noble","libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":true}
|
Security for aleph-alpha-inference 1.0.0
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.