- adding HNSW indexing method

- simultaneous search and reconstruction for IndexIVFPQ

- adding HNSW indexing method

- simultaneous search and reconstruction for IndexIVFPQ

- adding HNSW indexing method

- simultaneous search and reconstruction for IndexIVFPQ

just fixed a typo

various bugfixes from github issues
kmean with some frozen centroids
GPU better tiling for large flat datasets
default AVX for vector ops

various bugfixes from github issues
kmean with some frozen centroids
GPU better tiling for large flat datasets
default AVX for vector ops

various bugfixes from github issues
kmean with some frozen centroids
GPU better tiling for large flat datasets
default AVX for vector ops

* fixes for homebrew and anaconda python

* remove #/bin/bash

* PR feedback and handle different versions of LLVM

Accepting this 2-word PR without CLA....

fix index_cpu_to_gpu_multiple

fix PCA dimension

It took me quite some time to get around this error -- it might save others time.

* make INSTALL a proper markdown file

* add clarification to gpu test

* add forgotten parenthesis

- access GPU resources

- all Hamming distances of all sizes supported

- implemented ScalarQuantizer (without IVF)
- implemented update for IndexIVFFlat
- implemented L2 normalization preproc