Popular repositories Loading

1. PocketFlow PocketFlow Public

   Forked from Tencent/PocketFlow

   An Automatic Model Compression (AutoMC) framework for developing smaller and faster AI applications.

   Python

2. ROCm-Agent ROCm-Agent Public

   ROCm-Agent: Agentic RL for AMD GPU Kernel Optimization, inspired by https://cuda-agent.github.io/

   Python

3. autoresearch autoresearch Public

   Forked from karpathy/autoresearch

   AI agents running research on single-GPU nanochat training automatically

   Python

4. llm2vlm llm2vlm Public

   Finetuning LLMs into Vision-Language Models

   Python

5. ds4-rocm ds4-rocm Public

   Forked from antirez/ds4

   DeepSeek 4 Flash local inference engine for ROCm (specifically Strix Halo, gfx1151)

   C

6. FreeTokenHalo FreeTokenHalo Public

   Forked from FlashML-org/FreeToken, with AMD Strix Halo (gfx1151) ROCm support and kernel tuning

   Python