radix-attention

Here are 5 public repositories matching this topic...

gyunggyung / Agent.cpp

High-performance On-Device MoA (Mixture of Agents) Engine in C++. Optimized for CPU inference with RadixCache & PagedAttention. (Tiny-MoA Native)

c cpp moa on-device-ai llm llamacpp llama-cpp ggml paged-attention cpu-optimization mixture-of-agents radix-attention

Updated Jan 25, 2026
C++

JohnScheuer / radix-attention-sim

Star

Event-driven simulation of concurrent KV-cache prefix sharing, copy-on-write, prefix retention, and scheduler economics inspired by RadixAttention-style LLM serving systems.

python performance-engineering benchmark simulation scheduler inference systems gpu-memory serving copy-on-write event-driven-simulation kv-cache llm prefix-caching radix-attention

Updated Jul 23, 2026

Billy1900 / RadixMLA

Star

MLA-aware prefix caching for SGLang — exploit latent compression in RadixAttention (DeepSeek based model)

latent-space deepseek sglang-bankend radix-attention

Updated May 13, 2026
Python

JohnScheuer / request-reordering-cache-bench

Star

Event-driven benchmark of prefix-aware request reordering policies for LLM serving, measuring the ROI trade-off between prefix hit rate, prefill savings, and added queueing delay.

python performance-engineering benchmark simulation latency scheduler inference batching systems throughput serving prefill event-driven-simulation kv-cache llm prefix-caching radix-attention request-reordering

Updated Jul 24, 2026
Python

NagaYu / kvine

Star

Branch-aware KV cache treating agent trajectories as a persistent copy-on-write tree — research prototype (PyTorch + HF transformers)

transformers inference pytorch agents copy-on-write kv-cache llm llm-inference radix-attention

Updated Jul 17, 2026
Python

Improve this page

Add a description, image, and links to the radix-attention topic page so that developers can more easily learn about it.

Curate this topic

Add this topic to your repo

To associate your repository with the radix-attention topic, visit your repo's landing page and select "manage topics."

Learn more