t4a-cubecl-cuda
v0.10.2 ExperimentalTemporary tensor4all fork of CubeCL CUDA runtime
Quick Verdict
- โActively maintained (updated 3d ago)
- !Pre-1.0: API may have breaking changes
- โPermissive license (MIT OR Apache-2.0)
Security
Deep Insights
542 downloads in the last 30 days (18/day), up 158% from the previous period.
The primary maintainer publishes 59 crates. This suggests deep Rust expertise and long-term commitment to the ecosystem.
At 48KB, t4a-cubecl-cuda is lightweight. Small crate size correlates with focused, well-scoped functionality.
Notable dependents include tenferro-linalg, tenferro-gpu, t4a-cubecl. When high-quality crates choose t4a-cubecl-cuda, it's a strong quality signal.
Health Breakdown
Recency, release consistency, active ratio
Yanked ratio, deps, size, maturity, features
Reverse deps, ownership, ecosystem
Downloads, momentum, growth trend
Docs, repo, license, metadata
Download Trend
Top Dependents
Most downloaded crates that depend on t4a-cubecl-cuda
Version Adoption
Release Timeline
Feature Flags
default =["std", "cubecl-runtime/default", "cubecl-common/default", "cubecl-core/default"]