Decision Workspace
oxionnx-cuda vs oxicuda-infer vs tensorrt-infer
Side-by-side comparison of Rust crates
57
oxionnx-cuda
experimentalv0.1.7
CUDA-accelerated dispatch layer for oxionnx ONNX ops
48
oxicuda-infer
experimentalv0.5.5
High-performance GPU inference engine for OxiCUDA: PagedAttention KV cache, continuous batching, speculative decoding, structured sampling, and quantized inference.
43
tensorrt-infer
experimentalv0.1.0
Safe Rust wrappers for NVIDIA TensorRT inference
Core Metrics
| oxionnx-cuda | oxicuda-infer | tensorrt-infer | |
|---|---|---|---|
| Health Score | 57 | 48 | 43 |
| Total Downloads | 920 | 338 | 1.9K |
| 30d Downloads | 0 | 0 | 0 |
| Dependents | 7 | 0 | 6 |
| Releases | 7 | 19 | 1 |
| Last Updated | 57d ago | 57d ago | 209d ago |
| Age | 5m | 6m | 6m |
Health Breakdown
oxionnx-cuda
Maintenance
17
Quality
13
Community
8
Popularity
4
Documentation
15
oxicuda-infer
Maintenance
17
Quality
10
Community
6
Popularity
3
Documentation
12
tensorrt-infer
Maintenance
5
Quality
14
Community
8
Popularity
4
Documentation
12
Technical Details
| oxionnx-cuda | oxicuda-infer | tensorrt-infer | |
|---|---|---|---|
| Version | 0.1.7 | 0.5.5 | 0.1.0 |
| Stable (≥1.0) | ✗ No | ✗ No | ✗ No |
| License | Apache-2.0 | Apache-2.0 | MIT |
| Dependencies | 10 | 3 | 1 |
| Crate Size | 262KB | 146KB | 7KB |
| Features | 2 | 1 | 0 |
| Yanked % | 0.0% | 10.5% | 0.0% |
| Edition | 2021 | 2024 | 2024 |
| MSRV | 1.75 | 1.85 | 1.91.0 |
| Owners | 1 | 1 | 1 |
Links
Quick Verdict
- •oxionnx-cuda leads with a health score of 57/100, but none of the options score above 80.
- •tensorrt-infer has the most downloads (1.9K), suggesting wider adoption.