Popular repositories Loading

1. Triton-XDNA Triton-XDNA Public

   Forked from amd/Triton-XDNA

   Triton-XDNA with native Windows support - NPU kernel compilation & LLM inference on AMD Ryzen AI (Strix Halo)

   Python 3

2. qwen-asr-rocm qwen-asr-rocm Public

   Qwen3-ASR-0.6B speech-to-text service with vLLM, Flash Attention 2 (AMD triton), and Wyoming STT proxy for Home Assistant

   Python 2

3. FastFlowLM-Docker FastFlowLM-Docker Public

   Wyoming Protocol Docker container for FastFlowLM on AMD Ryzen AI NPUs — Whisper ASR + LLM conversation

   Shell 1

4. bitsandbytes bitsandbytes Public

   Forked from bitsandbytes-foundation/bitsandbytes

   Accessible large language models via k-bit quantization for PyTorch.

   Python

5. flash-attention flash-attention Public

   Forked from Dao-AILab/flash-attention

   Fast and memory-efficient exact attention

   Python

6. llm_assistant llm_assistant Public

   Home Assistant custom integration: OpenAI-compatible LLM conversation agent with MCP server support

   Python