vault81/redvault-ai
4
0
Fork 0
Code Issues 1 Pull requests 1 Projects 1 Releases Packages Wiki Activity

Bump foo

Browse source
This commit is contained in:
Tristan D. 2025-04-29 09:35:03 +02:00
parent 410edddef6
commit bd572a0ccd
Signed by: tristan
SSH key fingerprint: SHA256:3RU4RLOoM8oAjFU19f1W6t8uouZbA7GWkaSW6rjp1k8
4 changed files with 12 additions and 12 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

4
Cargo.lock generated
View file

@ -215,7 +215,7 @@ dependencies = [
[[package]] [[package]]
name = "axum-controller" name = "axum-controller"
version = "0.2.2" version = "0.2.1"
dependencies = [ dependencies = [
"axum-controller-macros", "axum-controller-macros",
"axum-typed-routing", "axum-typed-routing",
@ -223,7 +223,7 @@ dependencies = [
[[package]] [[package]]
name = "axum-controller-macros" name = "axum-controller-macros"
version = "0.2.2" version = "0.2.1"
dependencies = [ dependencies = [
"prettyplease", "prettyplease",
"proc-macro2", "proc-macro2",

8
flake.lock generated
View file

@ -64,16 +64,16 @@
] ]
}, },
"locked": { "locked": {
"lastModified": 1744745160, "lastModified": 1745868199,
"narHash": "sha256-tTfodLDvQslNA5irDmavbOnHsCyaQ3uQKxmsoKtrKdU=", "narHash": "sha256-kTy1oNcN4bNHDV7yqIOSTo/JUN4enHeqyUeVE/q4iHg=",
"owner": "ggerganov", "owner": "ggerganov",
"repo": "llama.cpp", "repo": "llama.cpp",
"rev": "80f19b41869728eeb6a26569957b92a773a2b2c6", "rev": "eaea3253244dc4bbe07f6cd81325847ccc6cf93e",
"type": "github" "type": "github"
}, },
"original": { "original": {
"owner": "ggerganov", "owner": "ggerganov",
"ref": "b5142", "ref": "b5214",
"repo": "llama.cpp", "repo": "llama.cpp",
"type": "github" "type": "github"
} }

2
flake.nix
View file

@ -19,7 +19,7 @@
flake-parts.url = "github:hercules-ci/flake-parts"; flake-parts.url = "github:hercules-ci/flake-parts";
devshell.url = "github:numtide/devshell"; devshell.url = "github:numtide/devshell";
llama-cpp = { llama-cpp = {
url = "github:ggerganov/llama.cpp/b5142"; url = "github:ggerganov/llama.cpp/b5214";
inputs.nixpkgs.follows = "nixpkgs"; inputs.nixpkgs.follows = "nixpkgs";
inputs.flake-parts.follows = "flake-parts"; inputs.flake-parts.follows = "flake-parts";
}; };

10
llama_proxy_man/config.yaml
View file

@ -48,12 +48,12 @@ model_specs:
args: args:
ctx-size: 16384 ctx-size: 16384
flash-attn: true flash-attn: true
model: /media/SanDisk/ai/models_live/mistralai_Mistral-Small-3.1-24B-Instruct-2503-IQ4_XS model: /media/SanDisk/ai/models_live/Qwen_Qwen3-30B-A3B-Q5_K_S.gguf
gpu-layers: 9999 gpu-layers: 9999
model-draft: /media/SanDisk/ai/models_live/Mistral-Small-3.1-DRAFT-0.5B.Q8_0.gguf # model-draft: /media/SanDisk/ai/models_live/Qwen_Qwen3-0.6B-Q6_K.gguf
gpu-layers-draft: 9999 # gpu-layers-draft: 9999
draft-max: 16 # draft-max: 16
draft-min: 4 # draft-min: 4
# - name: "big-chat" # - name: "big-chat"
# port: 18082 # port: 18082
# vram_usage: 26.5G # vram_usage: 26.5G