-
Hi,
Me and my friend have been reading the code for a while and we were looking for some ideas for contributing.
@ankane, you mentioned product quantization in #27. Is this still an issue? We would …
-
Currently CAGRA-Q does quantization after building the graph. This can certainly improve search performance. But it could be even better to improve build performance if distance computations while bui…
-
In 2013, there are two important improvements of Product Quantization. Optimized Product Quantization non-parametric solution [2] was equivalent to the Cartesian k-means [1] and performed better than …
-
## Description
I am trying to figure out if TensoRT and the `pytorch_quantization` module support post-training quantization for vision transformers.
The following piece of code follows the `pyt…
-
## Introduction
This document outlines a high level proposal for providing efficient, yet easy to use k-NN in OpenSearch in low-memory environments. Many more details to come in individual compone…
-
It's possible that I'm missing something due to unfamiliarity with the codebase, but it looks to me like vpq_dataset and train_pq are collapsing all the subspaces into a single codebook. E.g. if you …
-
I wanted to learn how product quantization works, and this repository provided excellent code to understand how it works. As I had been learning Rust for a few months now, I decided to re-write the `p…
-
I'm confused with the equation (12), what means the outer product of sw and sx? The activation is per-token quantization?
-
## 🐛 Bug
I followed instructions to use the Iterative Product Quantization provided here: (https://github.com/pytorch/fairseq/tree/master/examples/quant_noise)
I succeeded to create a transformer …
-
One of our customer is asking if we could consider supporting the following extension:
https://github.com/timescale/pgvectorscale
Thanks