harald/nixcfg
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity

feat(halo): inc. mtp to 6

Browse source
This commit is contained in:
Harald Hoyer 2026-05-19 06:38:24 +02:00
parent 46cdf2f6f6
commit 8bd096ff8d
1 changed files with 2 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

3
systems/x86_64-linux/halo/llama-server-27B-MTP.nix
View file

@ -46,7 +46,8 @@
"-c 262144"
"--fit on"
"--slot-save-path %C/llama-server/kv-slots-27B-MTP"
"--spec-type draft-mtp --spec-draft-n-max 2"
"--spec-type draft-mtp --spec-draft-n-max 6"
#"--spec-type ngram-mod --spec-ngram-mod-n-match 24 --spec-ngram-mod-n-min 48 --spec-ngram-mod-n-max 64"
];
Restart = "on-failure";
RestartSec = 10;