50
tq-kv
v0.6.0 ExperimentalTurboQuant KV Cache Compression for LLMs — First working on GGUF Q4_K_M (3-Fix framework). KV Compaction (50x token reduction). Per-head adaptive bitwidth. 4-bit value compression. Calibration pipeline. SRHT QJL (115x faster). AVX2 SIMD fused attention. C FFI. 114 tests.
MIT OR Apache-2.0 Edition 2021
Quick Verdict
- !Pre-1.0: API may have breaking changes
- ✓Permissive license (MIT OR Apache-2.0)
Security
Checking security advisories...
Downloads
264
Dependents
0
Releases
6
Size
76KB
Deep Insights
📊
Stable downloads
13 downloads in the last 30 days (0/day). Volume is roughly flat compared to the previous period.
Health Breakdown
Maintenance 15/25
Recency, release consistency, active ratio
Quality 16/25
Yanked ratio, deps, size, maturity, features
Community 6/20
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
Version Adoption
v0.5.0
43%
v0.6.0
27%
v0.4.0
11%
v0.3.0
10%
v0.1.0
9%
Release Timeline
6 releasessince 2026
J
F
M
A
M
J
J
A
S
O
N
D
2026
6
LessMore
Feature Flags
default =["std"]
ffistd*candlepython
README
Loading README...
Maintainers
Dependencies
6
direct dependencies
Dependents
0
crates depend on tq-kv