kvpress
✅ Recently maintainedLLM KV cache compression made easy
1,241Stars
192Forks
+27-day stars
Python · Apache-2.0 · Last push 2026-10-27
Official repository & installation ↗GitValue · Value evidence
Unscored · Evidence coverage 0%
Provisional rubric; documentation and runtime testing are separate. Missing evidence does not imply low value.
Star history
2025-09-292026-11-02
View historical data
| Date | Stars |
|---|---|
| 2026-10-04 | 1,224 |
| 2026-10-05 | 1,224 |
| 2026-10-06 | 1,224 |
| 2026-10-07 | 1,224 |
| 2026-10-08 | 1,224 |
| 2026-10-09 | 1,225 |
| 2026-10-10 | 1,226 |
| 2026-10-11 | 1,228 |
| 2026-10-12 | 1,228 |
| 2026-10-13 | 1,229 |
| 2026-10-14 | 1,230 |
| 2026-10-15 | 1,230 |
| 2026-10-16 | 1,230 |
| 2026-10-17 | 1,233 |
| 2026-10-18 | 1,233 |
| 2026-10-19 | 1,233 |
| 2026-10-20 | 1,235 |
| 2026-10-21 | 1,235 |
| 2026-10-22 | 1,236 |
| 2026-10-23 | 1,237 |
| 2026-10-24 | 1,237 |
| 2026-10-25 | 1,237 |
| 2026-10-26 | 1,239 |
| 2026-10-27 | 1,239 |
| 2026-10-28 | 1,240 |
| 2026-10-29 | 1,240 |
| 2026-10-30 | 1,240 |
| 2026-10-31 | 1,241 |
| 2026-11-01 | 1,241 |
| 2026-11-02 | 1,241 |
Get the project
git clone https://github.com/NVIDIA/kvpress.git
Related projects & alternative candidates
Related domains do not imply feature parity. Review official documentation and licenses.
vllm
High-throughput, memory-efficient LLM inference and serving engine that lets developers deploy models faster without building serving infrastructure.
★ 96,161sglangSGLang is a high-performance serving framework for large language models and multimodal models.
★ 38,385litellmCall 100+ LLM APIs using the OpenAI input/output format.
★ 62,514