Decision Workspace
oxicuda-dist-infer vs oxionnx-cuda vs ringkernel
Side-by-side comparison of Rust crates
48
oxicuda-dist-infer
experimentalv0.5.5
Distributed GPU inference for OxiCUDA: tensor parallelism, sequence parallelism, expert parallelism, distributed KV cache, and affinity-aware request routing.
57
oxionnx-cuda
experimentalv0.1.7
CUDA-accelerated dispatch layer for oxionnx ONNX ops
56
ringkernel
growingv1.1.0
GPU-native persistent actor model framework - Rust port of DotCompute Ring Kernel
Core Metrics
| oxicuda-dist-infer | oxionnx-cuda | ringkernel | |
|---|---|---|---|
| Health Score | 48 | 57 | 56 |
| Total Downloads | 315 | 920 | 1.3K |
| 30d Downloads | 0 | 0 | 0 |
| Dependents | 0 | 7 | 36 |
| Releases | 19 | 7 | 12 |
| Last Updated | 57d ago | 57d ago | 172d ago |
| Age | 6m | 5m | 10m |
Health Breakdown
oxicuda-dist-infer
Maintenance
17
Quality
10
Community
6
Popularity
3
Documentation
12
oxionnx-cuda
Maintenance
17
Quality
13
Community
8
Popularity
4
Documentation
15
ringkernel
Maintenance
11
Quality
16
Community
10
Popularity
4
Documentation
15
Technical Details
| oxicuda-dist-infer | oxionnx-cuda | ringkernel | |
|---|---|---|---|
| Version | 0.5.5 | 0.1.7 | 1.1.0 |
| Stable (≥1.0) | ✗ No | ✗ No | ✓ Yes |
| License | Apache-2.0 | Apache-2.0 | Apache-2.0 |
| Dependencies | 1 | 10 | 34 |
| Crate Size | 102KB | 262KB | 61KB |
| Features | 1 | 2 | 7 |
| Yanked % | 10.5% | 0.0% | 0.0% |
| Edition | 2024 | 2021 | 2021 |
| MSRV | 1.85 | 1.75 | 1.75 |
| 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.
- •ringkernel has the most downloads (1.3K), suggesting wider adoption.
- •oxicuda-dist-infer, oxionnx-cuda are pre-1.0 — API may change.