Decision Workspace
ruvllm_sparse_attention vs oxibonsai-model vs ruvector-attention-wasm
Side-by-side comparison of Rust crates
48
ruvllm_sparse_attention
experimentalv0.1.1
Subquadratic O(N log N) sparse attention kernel for Rust LLM inference on edge devices, with optional FastGRNN salience gating for near-linear O(N) scaling
59
oxibonsai-model
experimentalv0.2.2
Qwen3-8B Transformer implementation for OxiBonsai 1-bit inference
52
ruvector-attention-wasm
growingv2.1.0
High-performance WebAssembly attention mechanisms: Multi-Head, Flash, Hyperbolic, MoE, CGT Sheaf Attention with GPU acceleration for transformers and LLMs
Core Metrics
| ruvllm_sparse_attention | oxibonsai-model | ruvector-attention-wasm | |
|---|---|---|---|
| Health Score | 48 | 59 | 52 |
| Total Downloads | 28 | 669 | 106 |
| 30d Downloads | 0 | 0 | 0 |
| Dependents | 0 | 36 | 0 |
| Releases | 2 | 9 | 5 |
| Last Updated | 67d ago | 35d ago | 108d ago |
| Age | 2m | 3m | 7m |
Health Breakdown
ruvllm_sparse_attention
Maintenance
10
Quality
15
Community
6
Popularity
2
Documentation
15
oxibonsai-model
Maintenance
18
Quality
13
Community
10
Popularity
3
Documentation
15
ruvector-attention-wasm
Maintenance
15
Quality
16
Community
6
Popularity
2
Documentation
13
Technical Details
| ruvllm_sparse_attention | oxibonsai-model | ruvector-attention-wasm | |
|---|---|---|---|
| Version | 0.1.1 | 0.2.2 | 2.1.0 |
| Stable (≥1.0) | ✗ No | ✗ No | ✓ Yes |
| License | MIT | Apache-2.0 | MIT |
| Dependencies | 5 | 14 | 9 |
| Crate Size | 42KB | 432KB | 82KB |
| Features | 4 | 3 | 1 |
| Yanked % | 0.0% | 0.0% | 0.0% |
| Edition | 2021 | 2021 | 2021 |
| MSRV | 1.77 | 1.86 | — |
| Owners | 1 | 1 | 1 |
Links
Quick Verdict
- •oxibonsai-model leads with a health score of 59/100, but none of the options score above 80.
- •ruvllm_sparse_attention, oxibonsai-model are pre-1.0 — API may change.