Colibri runs mixture-of-experts language models on local hardware, streaming experts from disk with a small C engine.
Open source
24 alternativestensorflow-upstream
vsONNX-MLIR
tensorflow-upstream vs ONNX-MLIR
How do tensorflow-upstream and ONNX-MLIR compare? Here are the facts side by side: pricing, platforms, open-source status and what each one is for.
| Directory detail | tensorflow-upstream | ONNX-MLIR |
|---|---|---|
| What it is | The tensorflow-upstream repository provides a ROCm port of TensorFlow for the project. | ONNX-MLIR compiles ONNX models using MLIR compiler infrastructure for model deployment workflows. |
| Website | ||
| Type | Open-source project | Open-source project |
| Topic | ||
| Pricing | Not confirmed | Not confirmed |
| Platforms | Not recorded | Not recorded |
| Open source | Yes | Yes |
| Language | English | English |
| Alternatives |
Other options to consider
Sites similar to both tensorflow-upstream and ONNX-MLIR.
MII makes low-latency and high-throughput inference possible, powered by DeepSpeed.
Open source
24 alternatives
Glide provides an open model gateway for developing production generative AI applications.
Open source
24 alternatives
The colibri-core NLP tool and library works with n-grams, skipgrams, and other linguistic patterns.
Open source
24 alternatives
Gymnasium provides a standard API for single agent reinforcement learning environments and related utilities.
Open source
24 alternatives
Ollama runs language models locally and provides tools to work with model files and APIs.
Open source
24 alternatives