Prebuilt ARM64 Docker runtime archives for the AI Pod Qwen3-TTS LPK. Use runtime-orin-0.1.2.tar.gz on AGX Orin and runtime-thor-0.1.3.tar.gz on AGX Thor. These contain inference programs and their runtime dependencies; model weights are downloaded separately and mounted read-only. Verify the size and SHA256 in checksums.json, then import with docker load -i runtime-orin-0.1.2.tar.gz (or the Thor archive). Verify the imported image identity against checksums.json. Third-party license notices are retained in the archives. Runtime dependencies retain their respective third-party licenses, including NVIDIA runtime license terms. This repository does not relicense those files.
Independent publisher
Andy Stewart
manateelazycat
Models in Library8
Datasets in Library0
Models on Hugging Face24
Followers—
Compare the published evidence
This profile connects the 8 model and dataset records shown below to their upstream cards and sources. The library counts describe SAVRN's coverage, rather than this publisher's entire output.
Published tasks: Text to speech.
Reported licenses: mit, other. Open a record to review its specific license and conditions.
Compare model specifications, source dates, and hardware estimates on the individual records. Publisher identity verification is separate from a model's quality, deployment readiness, or suitability for your work.
Models
This is a Docker-save runtime archive for two NVIDIA Thor T5000 nodes with driver 595.78 and SM 11.0. It contains no model weights. Download the target and DFlash2 snapshots separately from the manateelazycat model repositories. The corresponding LPK uses the selected Hugging Face / ModelScope source for both model files and this archive. Public downloads require no hub login. The historical 0.5.0 reference environment was TensorFold 0.6.1 plus Mia 1.3.2 with the validated Thor decoder and communication patches. Default capacity is 1,048,576 tokens per request, a 2,684,928-token shared KV pool, and four streams. Reference acceptance includes empty-cache CUDA JIT, vision, structured output…
The current publication is in source/: original Engram safetensors copied server-side from deepseek-ai/DeepSeek-V4.1-Flash, with the upstream license, provenance and a pinned engram-manifest.json TP2 preparation recipe. The DeepSeek41 runtime prepares only its local rank, copying the original FP8 weight and scale bytes without numerical conversion. Full-file SHA256 checks must match all four TP2 packs from the accepted 192.168.1.160 / 192.168.1.134 deployment. These raw safetensors require the source-aware runtime; they are not directly consumable by the Engram pack reader. Older split-part files, if present at the repository root, are legacy artifacts. Use the exact files and revisions…
Built with Qwen. Non-commercial research and evaluation only. AuK code and speech weights are MIT. Required Qwen2.5-Omni-3B encoder is under the Qwen Research License. This release includes fixed model snapshots, model-free Orin/Thor runtime archives, controller, sources, licenses and minimal LPK. See licenses/NOTICE and all agreements before using or redistributing.