51
oxicuda-lm
v0.4.1 ExperimentalLarge language model inference primitives for OxiCUDA: BPE tokenizer, transformer layers with KV cache, GPT-2 and LLaMA architectures — pure Rust, zero CUDA SDK dependency.
Apache-2.0 Edition 2024 MSRV 1.85
Quick Verdict
- ✓Actively maintained (updated 6d ago)
- !Pre-1.0: API may have breaking changes
- ✓Permissive license (Apache-2.0)
Security
Checking security advisories...
Downloads
197
Dependents
0
Releases
13
Size
92KB
Deep Insights
📈
Strong growth momentum
84 downloads in the last 30 days (3/day), up 200% from the previous period.
👤
Prolific maintainer
The primary maintainer publishes 912 crates. This suggests deep Rust expertise and long-term commitment to the ecosystem.
⚠️
Notable yanked versions
15% of releases have been yanked. Check version history before pinning.
Health Breakdown
Maintenance 20/25
Recency, release consistency, active ratio
Quality 10/25
Yanked ratio, deps, size, maturity, features
Community 6/20
Reverse deps, ownership, ecosystem
Popularity 3/15
Downloads, momentum, growth trend
Documentation 12/15
Docs, repo, license, metadata
Download Trend
Daily downloads · last 90 days
0/day avg
Version Adoption
v0.4.0
24%
v0.1.6
20%
v0.4.1
20%
v0.1.4
19%
v0.1.7
17%
Release Timeline
10 releasessince 2026
J
F
M
A
M
J
J
A
S
O
N
D
2026
10
LessMore
Feature Flags
gpu-tests
README
Loading README...
Maintainers
Dependencies
5
direct dependencies
Dependents
0
crates depend on oxicuda-lm