ignis v0.1.0

Released 2026-09-19. The container image, the archives and the notes as written: the release on GitHub.

The first release that can be installed rather than built.

Container image (linux/amd64)

podman run --rm --device nvidia.com/gpu=all -p 8000:8000 \
  -v /path/to/models:/models:ro \
  -e IGNIS_ARTIFACT=/models/<name>.ninfer \
  ghcr.io/gpillon/ignis:0.1.0

(docker: --gpus all in place of --device.) The image carries the CUDA runtime but no driver — the host’s NVIDIA driver is injected by the container runtime. Without IGNIS_ARTIFACT it starts on the deterministic CPU mock, so running it with no model and no GPU is a smoke test of the image itself.

Every server flag has an IGNIS_* environment variable; anything after the image name is passed to the server, and --ui — a bare switch with no environment variable — is the image’s default command.

Binaries

The kernel is compiled for SM120a (RTX 5090 / Blackwell consumer) only, and the engine needs a .ninfer artifact, which is not part of this release. The Linux tarball needs the CUDA 13 runtime on the host; the Windows zip carries cudart64_13.dll. Both need an NVIDIA driver new enough for CUDA 13.

Each archive ships with a .sha256 sidecar.

Licensing

Apache-2.0 (LICENSE, NOTICE). The vendored reference ops keep their own terms — NOTICE-kernel, and kernel/vendor/manifest.json in the repo pins the reference commit and every vendored file’s content hash.