This PR is an integration of the quantization library into Qdrant:
https://github.com/qdrant/quantization

Quantization is a simplifying of vector data. It's helpful for reducing memory usage and scoring performance.

Quantization is enabled while segment creation uses a separate quantization config. For now, the config has only an enable flag.

curl -X PUT "http://$QDRANT_HOST/collections/test_collection" \
  -H 'Content-Type: application/json' \
  --data-raw '{
      "vectors": { ... },
      "quantization_config": {
        "enable": true
      }
    }' | jq

Quantized data is contained in RAM only, no mmap for quantized data for now. Quantized data is used for HNSW indexing and for HNSW search. Any search without HNSW index (plain search, exact search, etc) doesn't use quantized data.

For increasing accuracy, the user can disable quantized data using the ignore_quantization flag in search parameters. Because HNSW index is built using quantized data, ignore_quantization can just increase accuracy but not fix it to the original data accuracy.

If the search uses quantized data, final scores will be recalculated using the original data.

For memmap storage, there is RAM copy for deleted flags if quantization is enabled. Quantization on RAM is not effective when deleted flags are memmapped.

Perf and acc tests on real and random datasets are reported here:
https://www.notion.so/qdrant/7bit-quantization-in-hnsw-9f0467b5010849dcb359d0da93d844e0

All Submissions:

• Have you followed the guidelines in our Contributing document?
• Have you checked to ensure there aren't other open Pull Requests for the same update/change?

New Feature Submissions:

1. Does your submission pass tests?
2. Have you lint your code locally using cargo fmt command prior to submission?
3. Have you checked your code using cargo clippy command?

Changes to Core Features:

• Have you added an explanation of what your changes do and why you'd like us to include them?
• Have you written new tests for your core changes, as applicable?
• Have you successfully ran tests with your changes locally?