KTransformers
A Flexible Framework for Experiencing Heterogeneous LLM Inference/Fine-tune Optimizations
KTransformers scores 6.9/10 (Solid) in Inference & Serving.
Language Python License Apache-2.0 Stars 17.4k★ Type library Self-host Yes Repo kvcache-ai/ktransformers Homepage https://kvcache-ai.github.io/ktransformers
Quality
Solid 6.9
Adoption 56
Activity 71
Maturity 90
Community 54
Capability 50
Show the math
Overall 6.9/10
value = 6.9/10
score = value
Adoption 6/10
value = 56/100
score = 1 + 9 * value / 100
Activity 7.4/10
value = 70.8/100
score = 1 + 9 * value / 100
Maturity 9.1/10
value = 90.1/100
score = 1 + 9 * value / 100
Community 5.9/10
value = 54/100
score = 1 + 9 * value / 100
Capability 5.5/10
value = 50/100
score = 1 + 9 * value / 100
Key metrics
17.4k★ GitHub stars
62/90d Recent commits
21 devs/90d Recent contributors
1.9y Project age
active Last commit
Gotchas
No gotchas documented yet. Contribute one if you know a constraint we missed.
Labels
- Self-hosted
Self-hosted
You deploy and operate it yourself; there is no hosted option here.
moe offloading cpu-gpu local optimization