47,133 repositories indexed
1–5 of 5 · Most stars
Serve large Qwen models fast on the GPUs you actually own. Qwen3.8-27B on a single 24 GB card with vLLM: 127 tok/s single-user (381 when the answer quotes the prompt), ~1,035 tok/s at 64 concurrent, 150k-262k context. vLLM patches, requant pipeline, benchmarks.
A deep learning toolkit for healthcare AI: EHR (MIMIC, eICU, OMOP), clinical text, signals and imaging. 30+ models, reproducible pipelines.
Ontology-Augmented Generation for AI agents.
Decentralized agent memory for the Lightning economy. Nostr identity, L402 payments, MCP server.
Pipeline de ingestão e busca semântica de documentos para RAG — com rate limiting, circuit breaker e fila resiliente.