Decision Workspace
baracuda-flashinfer vs baracuda-flashinfer-sys vs ruvllm
Side-by-side comparison of Rust crates
Safe, typed Rust wrappers for NVIDIA FlashInfer's inference-serving kernels: batched paged-KV attention decode, decode-time KV-cache append, cascade / prefix-cache attention-state merge, and sort-free top-K / top-P / min-P sampling. The canonical vLLM-style serving surface for the baracuda CUDA stack. Apache-2.0 (FlashInfer upstream).
Raw C-ABI FFI surface for the vendored FlashInfer inference kernels (paged-KV decode, paged-KV append, cascade state merge, sort-free sampling). The launcher shims + vendored FlashInfer sources are compiled by `baracuda-kernels-sys`; this crate is a thin re-export facade so the FlashInfer C-ABI is reachable under its own crate name. Apache-2.0 (FlashInfer upstream) — see `crates/baracuda-kernels-sys/vendor/flashinfer/`.
LLM serving runtime with Ruvector integration - Paged attention, KV cache, and SONA learning
Core Metrics
| baracuda-flashinfer | baracuda-flashinfer-sys | ruvllm | |
|---|---|---|---|
| Health Score | 53 | 57 | 62 |
| Total Downloads | 394 | 509 | 54.1K |
| 30d Downloads | 0 | 0 | 0 |
| Dependents | 0 | 19 | 7 |
| Releases | 19 | 19 | 13 |
| Last Updated | 2d ago | 3d ago | 1d ago |
| Age | 4m | 4m | 10m |
Health Breakdown
Technical Details
| baracuda-flashinfer | baracuda-flashinfer-sys | ruvllm | |
|---|---|---|---|
| Version | 0.0.1-alpha.86 | 0.0.1-alpha.86 | 2.5.0 |
| Stable (≥1.0) | ✗ No | ✗ No | ✓ Yes |
| License | MIT OR Apache-2.0 | MIT OR Apache-2.0 | MIT |
| Dependencies | 5 | 1 | 46 |
| Crate Size | 24KB | 11KB | 1.3MB |
| Features | 2 | 2 | 29 |
| Yanked % | 0.0% | 0.0% | 0.0% |
| Edition | 2024 | 2024 | 2021 |
| MSRV | — | — | 1.77 |
| Owners | 1 | 1 | 1 |
Links
Quick Verdict
- •ruvllm leads with a health score of 62/100, but none of the options score above 80.
- •baracuda-flashinfer, baracuda-flashinfer-sys are pre-1.0 — API may change.