Evan Reichard 88308602c8 feat(llama-swap): add concurrent model matrix for CUDA0/CUDA1 ...

Allow one CUDA0 and one CUDA1 model to run simultaneously. Dual-GPU
models (using -ts splits) are excluded from the matrix so they evict
everything when loaded. vLLM docker models get evict_cost=50 to
discourage eviction due to slow cold starts.

2026-05-01 16:50:28 -04:00

..

common

feat: comprehensive NixOS and home-manager configuration updates

2025-12-14 16:24:11 -05:00

display-managers/sddm

fix: sddm theme

2026-01-07 12:04:41 -05:00

hardware

chore: utlity update

2026-01-20 21:18:59 -05:00

home

Migrate to Snowfall (#1)

2025-04-21 00:56:53 +00:00

nix

Migrate to Snowfall (#1)

2025-04-21 00:56:53 +00:00

programs/graphical/wms/hyprland

feat(systems): add work vm

2026-04-06 14:15:11 -04:00

security/sops

chore(cleanup): sops, opencode, etc

2026-01-11 22:19:31 -05:00

services

feat(llama-swap): add concurrent model matrix for CUDA0/CUDA1

2026-05-01 16:50:28 -04:00

system

refactor(nixos): move supportedFilesystems nfs to common boot module

2026-04-24 07:25:06 -04:00

user

Migrate to Snowfall (#1)

2025-04-21 00:56:53 +00:00

virtualisation

update llamacpp

2026-01-20 20:20:50 -05:00