Popular repositories Loading

1. vllm-factory vllm-factory Public

   Production inference for encoder models - ColBERT, GLiNER, ColPali, embeddings etc. - as vLLM plugins for online and in-process deployment

   Python 87 10

2. colsearch colsearch Public

   High-performance late-interaction retrieval engine for on-prem AI. ColBERT/ColPali multi-vector search with Rust fused MaxSim, Triton GPU kernels, ROQ quantization, LEMUR routing, WAL-backed CRUD, …

   Python 17 1

3. latence latence Public

   Turn messy enterprise documents into structured, embedded, provenance-carrying RAG corpus (including PII redaction) and an evidence-linked knowledge graph. All as plain Parquet files you own.

   Python 14 1

4. latence-trace-python latence-trace-python Public

   Python 1

5. chatbot-facebook-nodejs chatbot-facebook-nodejs Public archive

   Forked from ivabb/chatbot-facebook-nodejs

   JavaScript

6. LongLoRA LongLoRA Public archive

   Forked from JIA-Lab-research/LongLoRA

   Code and documents of LongLoRA and LongAlpaca

   Python