Files
nix/modules/nixos/services
Evan Reichard 81ffe67cce refactor(llama-swap): replace --parallel with -np and add -kvu flag
Switch llama-server invocations from --parallel to -np with -kvu
(kv-cache unified) across Qwen3.6 model configs. Also reduce
context for qwen3.6-27b-cuda0 from 150k to 140k.
2026-05-19 06:22:08 -04:00
..
2025-04-21 00:56:53 +00:00
2025-04-21 00:56:53 +00:00
2025-09-19 14:37:17 -04:00
2025-09-23 19:23:35 -04:00
2025-04-21 00:56:53 +00:00
2026-01-23 18:32:10 -05:00
2025-12-26 20:51:59 -05:00
2025-09-22 19:05:18 -04:00
2025-09-07 15:20:47 -04:00
2025-04-21 00:56:53 +00:00