verifiedhigh · 0.85updated 2026-10-03

llama.cpp HTTP server README (embedding pooling + rerank)

repo

Fields

sources/embed-llamacpp-server-readme

URL

https://github.com/ggml-org/llama.cpp/blob/master/tools/server/README.md

Publisher

ggml-org

Kind

repo

Accessed

2026-10-03

notes

llama.cpp tools/server README. Documents --pooling {none,mean,cls,last,rank}, an OpenAI-compatible embeddings route, and a reranking endpoint (PR ggml-org/llama.cpp#9510).

Notes

llama.cpp tools/server README. Documents --pooling {none,mean,cls,last,rank}, an OpenAI-compatible embeddings route, and a reranking endpoint (PR ggml-org/llama.cpp#9510).

Cross-references

This record references no other records.