Archive

Serving

ZML is a production inference stack, purpose-built to decouple AI workloads from proprietary hardware.

01

engineering

zml/llmd 2026.11.3

Embeddings, decisions, and MXFP4/NVFP4 on Intel.

Nov 19, 2026 inference / serving
02

engineering

zml/llmd 20261112.0

More drafts, faster prefill.

Nov 12, 2026 inference / serving
03

engineering

zml/llmd 20261106.0

More models, less waiting.

Nov 6, 2026 inference / serving
05

engineering

zml/llmd 20261023.0

More speed, more models, more fun.

Oct 22, 2026 inference / serving
06

engineering

zml/llmd 20261009.0

Performance is all around me, and so the feeling grows.

Oct 9, 2026 inference / serving
07

engineering

zml/llmd 20260929.0

DeepSeek-V4.1-Flash lands on NVIDIA and AMD.

Sep 29, 2026 inference / serving