48
katgpt-hla
v0.1.3 ExperimentalHigher-order Linear Attention (HLA) substrate — O(1) inference cache types and streaming kernels. Pure substrate, depends only on katgpt-types (Config + SIMD).
MIT Edition 2024
Quick Verdict
- ✓Actively maintained (updated 48d ago)
- !Pre-1.0: API may have breaking changes
- ✓Tiny footprint (17KB, 2 deps)
- ✓Permissive license (MIT)
Security
Checking security advisories...
Downloads
143
Dependents
4
Releases
4
Size
17KB
Deep Insights
📉
Download decline
23 downloads in the last 30 days, down 49% from the previous period. May indicate migration to alternatives.
🪶
Minimal dependencies
Only 2 direct dependencies. Lean dependency tree means faster builds and lower supply chain risk.
📐
Compact crate
At 17KB, katgpt-hla is lightweight. Small crate size correlates with focused, well-scoped functionality.
Health Breakdown
Maintenance 11/25
Recency, release consistency, active ratio
Quality 16/25
Yanked ratio, deps, size, maturity, features
Community 8/20
Reverse deps, ownership, ecosystem
Popularity 3/15
Downloads, momentum, growth trend
Documentation 10/15
Docs, repo, license, metadata
Download Trend
Daily downloads · last 90 days
0/day avg
Top Dependents
Most downloaded crates that depend on katgpt-hla
Version Adoption
v0.1.3
34%
v0.1.1
26%
v0.1.2
22%
v0.1.0
19%
Release Timeline
4 releasessince 2026
J
F
M
A
M
J
J
A
S
O
N
D
2026
4
LessMore
Feature Flags
serde
README
Loading README...
Maintainers
Dependencies
2
direct dependencies
Dependents
4
crates depend on katgpt-hla