500+ models · Compile once, run anywhere · AI model serving on RBLN NPUs

RBLN Model Zoo

Quick Start

The rbln-zoo CLI discovers models; each model is run from its own directory.

1. Discover — install the CLI and browse the catalog:

git clone https://github.com/RBLN-SW/rbln-model-zoo.git && cd rbln-model-zoo
uv pip install -e .

rbln-zoo list -s llama      # search the catalog
rbln-zoo cards              # show card types

2. Run — from the model's directory, install its dependencies and execute:

cd huggingface/transformers/text2text-generation/llama/llama3.1-8b
uv pip install -r requirements.txt
python compile.py && python inference.py     # single-file examples: python main.py

[!IMPORTANT] Compilation requires the RBLN Compiler from RBLN's private package index. See the installation guide.

CLI

rbln-zoo browses and filters the model catalog; it does not compile or run models.

rbln-zoo list -c RBLN-CA22 -t text2text-generation -s qwen   # filter by card, task, keyword
rbln-zoo cards                                               # card types and counts

Card types

Models are tagged with RBLN product cards — RBLN-CA22 (ATOM™+) and RBLN-CA25 (ATOM™-Max) — per the version matrix. Matching is case-insensitive and honors aliases declared in model_registry.yaml.

cards:
  RBLN-CA22:
    description: "ATOM™+"
  RBLN-CA25:
    description: "ATOM™-Max"
  CX:
    description: "Next-gen NPU"
    aliases: [RBLN-CX01]   # -c RBLN-CX01 resolves to CX

default_cards: [RBLN-CA22, RBLN-CA25]

overrides:
  huggingface/transformers/.../model-a:
    cards: [RBLN-CA25, CX]

Ecosystems

[!NOTE] Model counts are approximate, as of 2026-07-13 — see the Model Zoo for the live catalog.

C API — C/C++ inference bindings; install via APT, then build from source.

Deployment

Compile a model, then serve it on a supported inference server.

vLLM RBLN

cd huggingface/transformers/text2text-generation/llama/llama3.1-8b
python compile.py
uv pip install \
  --extra-index-url https://wheels.vllm.ai/0.24.0/cpu \
  --torch-backend cpu \
  vllm-rbln

from vllm import LLM, SamplingParams

llm = LLM(model="Llama-3.1-8B-Instruct")
out = llm.generate(["Hello"], SamplingParams(max_tokens=64))
print(out[0].outputs[0].text)

[!NOTE] Install commands are current as of 2026-07-13 and follow the vLLM RBLN install guide — see it for the latest.

Other serving options

• NVIDIA Triton Inference Server — multi-model inference
• TorchServe — PyTorch model serving

Links

• CHANGELOG — release history
• Issues — report bugs, request features or new models