TranslatedUsing dense-compute cards to accelerate sparse, large-VRAM hosts, where the hosts include AI Max+ 395, M3 512G, DGX Spark, and others.
- llama-cpp
- pipeline-parallelism
- prefill-decode
- rtx-3060
Repository Index
47,133 repositories indexed
1–3 of 3 · Most stars
Ontology-Augmented Generation for AI agents.
- agent-skills
- document-parsing
- knowledge-graph
- mineru
DeepSeek-V4.1-Flash-1017 EXL3 on 2x DGX Sparks with TensorFold