#kv-cache-optimization Repositories
Discover 9 active open source GitHub repositories tagged with #kv-cache-optimization, accumulating 13,361 total stars (averaging 1,484 stars per project). Leading this topic is deepseek-ai/DeepSeek-V2 with 4,988 stars.
9 repositories total
DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model
[NeurIPS'24 Spotlight, ICLR'25, ICML'25] To speed up Long-context LLMs' inference, approximate and dynamic sparse calculate the attention, which reduces inference latency by up to 10x for pre-filling on an A100 while maintaining accuracy.
Frequently Asked Questions
What is the most popular #kv-cache-optimization repository on GitHub?
The top ranked open source #kv-cache-optimization project on GitHub is deepseek-ai/DeepSeek-V2 with 4,988 stars. DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model
Which programming languages are most used in #kv-cache-optimization repositories?
Among the top ranked #kv-cache-optimization projects on GitHub, the most common programming languages are Python, Jupyter Notebook.
How is the #kv-cache-optimization repository ranking calculated?
We track 9 active open source repositories tagged with #kv-cache-optimization (500+ stars), totaling 13,361 stars with an average of 1,484 stars per repository. Rankings update daily from the GitHub API.