osmarks/documentation
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

Edit ‘autogollark’

Browse Source
This commit is contained in:
osmarks
2026-06-10 18:09:45 +00:00
committed by wikimind
parent 1dff5bedc7
commit c9bac1754c
1 changed files with 2 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files
autogollark.myco
+2 -1
View File
@@ -37,9 +37,10 @@ Autogollark currently comprises the dataset, the search API server and the [[htt
* https://arxiv.org/abs/2507.07101
* https://arxiv.org/abs/2507.01335
* https://arxiv.org/abs/2510.14901
* https://github.com/d0rc/egg.c and https://eshyperscale.github.io/. Does this actually work (at scale)? Why? Would be really nice for using AMX units.
* https://github.com/d0rc/egg.c and https://eshyperscale.github.io/. Does this actually work (at scale)? Why? Would be really nice for using AMX units. But no pretrained models.
* Maybe compute grants are available for training.
* Substantial bandwidth bottleneck on CPU (230GB/s nominal; 200GB/s benchmarked; 100GB/s per NUMA node, which llama.cpp handles awfully). Specdec/MTP would be useful. Can anything use AMX well though?
* https://dnhkng.github.io/posts/rys/
}
* Search over conversations with non-gollark simulacra? Should find //something// to use spare parallelism on local inference. Best-of-n? https://arxiv.org/abs/2505.10475
* {Longer context, mux several channels.