Popular repositories Loading

1. strix-halo-lemonade-benchmarks strix-halo-lemonade-benchmarks Public

   Four-part benchmark deep-dive* of the Lemonade Server + llama.cpp/Vulkan + vLLM inference stack on the ASUS ROG Flow Z13 GZ302EA

   Python 1

2. RAG-NPU-Liquid RAG-NPU-Liquid Public

   Production-ready RAG pipeline for AMD Ryzen AI Max+ 395

   Python 1

3. Lemonade-AI-Server-Benchmark-Report-Multi-Token-Prediction-MTP- Lemonade-AI-Server-Benchmark-Report-Multi-Token-Prediction-MTP- Public

   This report compiles comprehensive benchmarks comparing Multi-Token Prediction (MTP) models with standard models, and quantifies the performance impact of speculative decoding across different gene…

   Python

4. FastFlowLM-npu-benchmark FastFlowLM-npu-benchmark Public

   Benchmarking LLM inference on the AMD XDNA2 NPU (50 TOPS) using FastFlowLM on the ASUS ROG Flow Z13 — Ryzen AI Max+ 395 / Strix Halo. Results for 12 models (1B–20B) across multiple ▎ context length…

   Python

5. lemonade-strix-halo-power-efficiency lemonade-strix-halo-power-efficiency Public

   Power efficiency benchmarks (Tokens/Joule) for the Lemonade Local AI Stack on the AMD Ryzen AI Max+ 395 (Strix Halo).

   Python

6. lemonade-Agent-Manager lemonade-Agent-Manager Public

   Forked from lemonade-sdk/lemonade

   Lemonade helps users discover and run local AI apps by serving optimized LLMs right from their own GPUs and NPUs. Join our discord: https://discord.gg/5xXzkMu8Zk

   C++