eBPF uprobe 기반 CUDA/HIP 통합 트레이싱으로 오버헤드 2% 미만 달성
Same eBPF, Different Vendor: Tracing libhip Calls on AMD ROCm
Same eBPF, Different Vendor: Tracing libhip Calls on AMD ROCm
I Put Gemma 4 Behind My Homelab AI Gateway. This Is the Beginning.
CyberSecQwen-4B: Why Defensive Cyber Needs Small, Specialized, Locally-Runnable Models
MedQA: Fine-Tuning a Clinical AI on AMD ROCm — No CUDA Required
ROCm의 musl/mimalloc 기반 포팅을 통한 고보안 런타임 빌드 구현
AMD 하드웨어 최적화, 멀티모달 통합 로컬 LLM 서버 Lemonade
Easily Build and Share ROCm Kernels with Hugging Face
AMD + 🤗: Large Language Models Out-of-the-Box Acceleration with AMD GPU
Hugging Face and AMD partner on accelerating state-of-the-art models for CPU and GPU platforms
Run a Chatgpt-like Chatbot on a Single GPU with ROCm