AIPython★ 271⑂ 84 forks
AMD-AGI/Hyperloom
HYPERLOOM AUTO-OPTIMIZATION LLM ON AMD
Hyperloom — agentic system that automatically optimizes LLM workloads on AMD GPUs by selecting kernels and tuning parameters for peak performance without manual setup.
// KEY FEATURES
- Automatically selects optimal GPU cores for specific LLM models on AMD.
- Reduces latency and increases throughput via dynamic parameter tuning.
- Integrates with PyTorch and TensorFlow through a simple API for quick integration.
- Provides real-time GPU profiling and visualization of resource usage.
#agent#ai-agents#amd#amd-gpu#gpu#gpu-kernels#hip#inference#large-language-models#llm#llm-inference#machine-learning
Open on GitHub →New repositories every 30 minutes
REDDYX AI scans GitHub 24/7 and ships the best AI/ML/Web3 projects to Telegram.
Join on Telegram