AI & LLM Engineering · vLLM · By amd

Build the standalone ZenDNN native library (zendnnl) from source with the alternate compute backends OFF (no oneDNN, libxsmm, parlooper, fbgemm), keeping AOCL DLP, which is the GEMM backend zendnnl…

amd/ZenDNN

Serves AI models on AMD Instinct GPU hardware using vLLM. An agent skill from amd/skills.

amd/skills

Build vLLM (CPU) end-to-end with the oneDNN + ZenDNN (zen64) backend via direct integration (NO zentorch).

amd/ZenDNN

Run, resume, monitor, diagnose, and report Quark Quant-Perf workflows for PyTorch and HuggingFace transformers models.

amd/Quark

Serves an LLM on a supported AMD EPYC server CPU using vLLM with zentorch, in Docker, Podman, or conda.

amd/skills

Autonomously optimizes end-to-end LLM inference throughput on AMD Instinct GPUs and reports a validated gain, using the Hyperloom multi-agent optimizer.

amd/skills

Benchmarks LLM inference and drives GPU kernel optimization with Magpie.

amd/skills

End-to-end LLM accuracy evaluation on AMD ROCm (ROCm-only) — container setup, vLLM/SGLang/ATOM serving, lm-eval / lighteval / evalscope benchmarks.

amd/Quark