mesibo

What are the differences in this library from the original Hieu Rocker's library? Thanks

### What happened? We accidentally passed the embedding model (nomic-embed-text-v1.5) in the -m parameter, which caused the server to crash. `./llama-server -m /data/ollama-models/models/blobs/sha256-970aa74c0a90ef7482477cf803618e776e173c007bf957f635f1015bfcfef0e6 --path ./examples/server/public/` ### Name and Version version:...

[Question]: Build Procedure on RHEL/Rocky 8 Without Docker + C/C++ API Access

1

1. We want to build infinity on RHEL/Rocky 8 without using Docker. Could you please provide a build procedure or any relevant documentation that can help us with this setup?...

Missing configuration for Milvus (Knowhere) on GitHub repo

1

When running benchmarks locally, we noticed a discrepancy between how Milvus is represented on the ann-benchmarks website versus what's produced when running the benchmark code from the repository. The ann-benchmarks...

The current implementation of `get_memory_usage()` in `BaseANN` uses `psutil.Process().memory_info().rss` to measure memory usage, which may not accurately represent the actual memory consumption when using memory-mapped indexing. We are testing our...

SIFT database accuracy used in benchmarks

1

I am looking for some feedback on the accuracy of the SIFT database used in ann-benchmark here. Since it has been used for benchmarking, I assumed it to be quite...

Proposal: Remove Single Query Mode for Better Flexibility

2

Hi, I am filing this issue to propose simplifying ann_benchmarks by maintaining only one mode instead of the current single and batch modes and presenting unified benchmarking results independent of...

Support Multi-threaded Benchmarks for Production-Realistic Performance Metrics

5

Currently, `ANN-Benchmarks` enforces single-CPU execution during experimentation, disabling multi-threading capabilities at the hardware level (AWS single-cpu mode) so that even libraries supporting multi-core CPU/threading can't use it. While batch mode...

We are testing HNSW and have a question about the parameter passed to the `getNeighborsByHeuristic2()`. Should the number of elements selected by the heuristic be `Mcurmax` instead of `M_`? The...