Edit ‘good_ideas’: Synced 1769415285204

This commit is contained in:
sync
2026-01-26 08:44:22 +00:00
committed by wikimind
parent 3cb6e1a20c
commit 02a410de6a

View File

@@ -102,6 +102,7 @@ Graph-based vector indices do beam search on a graph constructed so that beam se
* We can also pack the graphs better (with some cost at retrieval time due to multi-page accesses and more compute): sorting and delta compression of node indices, offload metadata again, maybe general-purpose compressors, maybe QAT/IAA codecs, quantize the graph vectors a bit.
* 100μs/node is assuming SSD random latency, and with that assumption these algorithms still aren't useful if we can throw more time at it because we can do more reads. But with really clever pathfinding, HDDs could also work. Maybe? Two orders of magnitude slower, though.
* https://arxiv.org/pdf/2501.10479
* Also see the Jina spherical compression thing.
}
* SAEs/dictionary learning algorithms for residual quantization.
* Minecraft/Factorio crossover modpack via Clusterio-like thing.