-
Hi!, I would like if is possible apply the 8 bit strategy to Prodigy to reduce the vram used. Or it could mess something necessary for make it works. I don't understand very well the paper and I'd rea…
-
Hi! I noticed this project and that it's positioned as a successor to pgvecto.rs. I'm interested to learn more about how it compares in terms of performance and recall.
I also see that it only suppor…
-
### Description
I'm working on #13519, and ran `gradle tidy` to ... tidy things up, and it does this:
```
// verifies it's fine to change your mind on the number of bits quantization you want f…
-
[https://github.com/jakevdp/klsh/blob/master/klsh/hamming_ann.py#L163](url)
I have a doubt regarding your implementation of HammingANN. Your are not permuting the query bit vectors for HammingANN but …
ghost updated
8 years ago
-
Hi, thanks for the interesting work.
I'm playing a bit with the code on a simple single-class dataset of 256x256 images, and I've modified basic things (imagenet hardcoded numbers, etc...).
I'm …
-
In [`array_inequlities`](https://github.com/GaloisInc/saw-script/blob/013f9f9ba03b055cb548bc980fd4e029cb544867/heapster-saw/examples/arrays_proofs.v#L45) I propose a strategy to solve signed inequalit…
-
Currently the read interface of Java Arrow Vector is quite slow because the access operation has to go through validity bit check and boundary check before it can actually load the data. Such a safety…
-
### What is the issue?
I'm working on a RAG written in Python, and we're using ollama as the chatbot LLM provider. It's running in a Docker container and the Python app makes REST API calls to it. We…
-
InvertedIndex implemented in #77 is optimized for storing sparse vectors where most of the dimensions have 0 value. To check and improve performance of the index we need benchmark it against a realist…
twitu updated
2 months ago
-
This issue has been filed to give consideration to the possibility of adding more off-heap vector scorers.
We recently added a MemorySegment Vector scorer for scoring byte vectors without copying …