Popular repositories Loading

1. gpu-inference-engine gpu-inference-engine Public

   High-throughput LLM inference engine optimized for AMD Instinct MI300X GPUs

   Python

2. rocm-kernel-suite rocm-kernel-suite Public

   Collection of optimized ROCm HIP kernels for matrix operations on AMD GPUs

   C++

3. distributed-training-framework distributed-training-framework Public

   Scalable distributed training framework with FSDP and pipeline parallelism for AMD GPUs

   Python

4. amd-mi300x-benchmark-suite amd-mi300x-benchmark-suite Public

   Comprehensive benchmark suite for AMD Instinct MI300X GPUs — memory, compute, interconnect

   Python

5. multimodal-vision-transformer multimodal-vision-transformer Public

   Vision-language model with SigLIP + LLaMA for multimodal inference on AMD GPUs

   Python

6. data-parallel-etl data-parallel-etl Public

   GPU-accelerated ETL pipeline for processing petabyte-scale datasets with Polars and RAPIDS

   Python