Decision Workspace
oxicuda-infer vs oxionnx-cuda vs oxicuda-train
Side-by-side comparison of Rust crates
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.
57
oxionnx-cuda
experimentalv0.1.7
CUDA-accelerated dispatch layer for oxionnx ONNX ops
47
oxicuda-train
experimentalv0.5.5
GPU-accelerated training engine: fused optimizer update kernels, gradient checkpointing, LR schedulers, and ZeRO optimizer state sharding
Core Metrics
| oxicuda-infer | oxionnx-cuda | oxicuda-train | |
|---|---|---|---|
| Health Score | 48 | 57 | 47 |
| Total Downloads | 338 | 920 | 336 |
| 30d Downloads | 0 | 0 | 0 |
| Dependents | 0 | 7 | 0 |
| Releases | 19 | 7 | 19 |
| Last Updated | 57d ago | 57d ago | 57d ago |
| Age | 6m | 5m | 6m |
Health Breakdown
oxicuda-infer
Maintenance
17
Quality
10
Community
6
Popularity
3
Documentation
12
oxionnx-cuda
Maintenance
17
Quality
13
Community
8
Popularity
4
Documentation
15
oxicuda-train
Maintenance
17
Quality
9
Community
6
Popularity
3
Documentation
12
Technical Details
| oxicuda-infer | oxionnx-cuda | oxicuda-train | |
|---|---|---|---|
| Version | 0.5.5 | 0.1.7 | 0.5.5 |
| Stable (≥1.0) | ✗ No | ✗ No | ✗ No |
| License | Apache-2.0 | Apache-2.0 | Apache-2.0 |
| Dependencies | 3 | 10 | 9 |
| Crate Size | 146KB | 262KB | 134KB |
| Features | 1 | 2 | 3 |
| Yanked % | 10.5% | 0.0% | 10.5% |
| Edition | 2024 | 2021 | 2024 |
| MSRV | 1.85 | 1.75 | 1.85 |
| 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.