# zml/llmd 2026.11.3

> Source: <https://zml.ai/posts/llmd-2026.11.3/>
> Published: 2026-11-19 05:00:00+00:00

**Key takeaway:** zml/llmd 2026.11.3 adds POST /v1/embeddings and POST /embeddings with Qwen3-Embedding support, accepting a single string or list of strings and a dimensions parameter for smaller output vectors where the model supports it.

We are pleased to announce the release of `zml/llmd 2026.11.3`. This week brings an embeddings API, support for
decision models, and MXFP4/NVFP4 on Intel oneAPI. You’ll also find general bug fixes and improvements throughout.

The version number looks a little different this week. Releases now use `YYYY.MM.<revision>`,
with a revision number for each release within the month.

zml/llmd now implements the embeddings endpoints through `POST /v1/embeddings` and `POST /embeddings` with initial
support for the [Qwen3-Embedding](https://huggingface.co/collections/Qwen/qwen3-embedding) series.
You can pass a single string or a list of strings and request a smaller output vector with `dimensions`
when the model supports it.
