Sparse Embedding Compression for Scalable Retrieval in Recommender Systems
-
Updated
Nov 21, 2025 - Python
#
embedding-compression
Here are 9 public repositories matching this topic...
Near-optimal vector quantization from Google's ICLR 2026 paper — 95% recall, 5x compression, zero preprocessing, pure Python FAISS replacement
python machine-learning information-retrieval compression deep-learning numpy quantization semantic-search similarity-search vector-quantization faiss rag vector-database kv-cache ann-search llm approximate-nearest-neighbor embedding-compression iclr-2026 turboquant
-
Updated
Mar 28, 2026 - Python
Vector compression with TurboQuant codecs for embeddings, retrieval, and KV-cache. 10x compression, pure NumPy core — optional GPU acceleration via PyTorch (CUDA/MPS) or MLX (Metal).
retrieval quantization vector-database kv-cache llm-inference embedding-compression turboquant vector-compression qjl semafold
-
Updated
Sep 13, 2026 - Python
Product Quantization (PQ) vector compression engine partitioning embeddings into discrete codebook indices
mcp developer-tools ann quantization product-quantization python-standard-library vector-db agent-skills embedding-compression vector-compression codebook-quantizer
-
Updated
Sep 29, 2026 - Python
Product Quantization (PQ) vector compression engine partitioning embeddings into discrete codebook indices
mcp developer-tools ann quantization product-quantization python-standard-library vector-db agent-skills embedding-compression vector-compression codebook-quantizer
-
Updated
Sep 29, 2026 - Python
Compress embeddings, retrieval vectors, and KV-cache with TurboQuant codecs for 10x smaller storage and NumPy-first AI workloads
swift machine-learning retrieval transformers pytorch moe quantization vector-database kv-cache openai-api llm-inference qwen embedding-compression turboquant qjl semafold
-
Updated
Oct 12, 2026 - Python
A PyTorch Framework for Sparse Representation Learning
machine-learning pytorch representation-learning recommender-systems sparse-autoencoders interpretability sparse-representations embedding-compression sparse-embeddings
-
Updated
Sep 27, 2026 - Python
TurboQuant (ICLR 2026) vector quantization for memory/RAG embedding compression | 5-8x压缩 98%+召回率 | numpy only, no GPU
numpy vector-quantization rag embedding-compression memory-search iclr2026 openclaw hadamard-transform turboquant
-
Updated
Mar 27, 2026 - Python
TensoRAG: High-performance Python engine for vector compression & fast RAG search via ML-GSVD. Reduces RAM up to 91%, speeds up search 14x. Independent, private hobby project implementing the PhD findings of Dr. L. Khamidullina (TU Ilmenau); no official affiliation with the author or university.
machine-learning numpy tensor-decomposition gsvd rag vector-search vector-database tensor-decomposition-algorithms llm-compression embedding-compression rag-search vector-compression
-
Updated
Sep 10, 2026 - Python
Add this topic to your repo
To associate your repository with the embedding-compression topic, visit your repo's landing page and select "manage topics."