Search
Have an existing account?
Sign In
Tag: embeddings
Linkup ships a sparse retriever that trains on one GPU
SPARSEUP packs a 149M-parameter encoder under Apache 2.0 weights and reports 56.4 average nDCG@10 on BEIR-13.
Pinecone open-sources a recipe book for vector quantization
Pinecone has published an MIT-licensed framework that rebuilds 25 common quantizers from seven shared primitives.
Perplexity reuses LLM kernels to keep embedding serving cheap
Engineers at Perplexity detail a GPU stack where batch and online embedding workloads borrow prefill and decode paths.