alexpires.me/a13labs.infra
1
0
Fork 0
Code Issues Pull Requests 1 Actions Packages Projects Releases Wiki Activity

auto_suspend: busctl->shutdown now, 1min timer config, AMD JSON parsing, locale fix, unit tests

Browse Source
This commit is contained in:
Alexandre Pires
2026-06-09 20:45:08 +02:00
parent f8a0a8ab1f
commit 80c154df03
9 changed files with 701 additions and 81 deletions
Download Patch File Download Diff File Expand all files Collapse all files
ansible/host_vars/gpu-01.lab.alexpires.me.yml
+25 -20
View File
@@ -132,103 +132,103 @@ llama_server_models:
quant: "Q8_0"
revision: "main"
preset:
ctx-size: 131072
ctx-size: 98304
- name: "gemma-4-26b-a4b-ud-iq4-xs"
model_id: "unsloth/gemma-4-26B-A4B-it-GGUF"
quant: "UD-IQ4_XS"
revision: "main"
preset:
ctx-size: 131072
ctx-size: 98304
- name: "gemma-4-31b-iq4-xs"
model_id: "unsloth/gemma-4-31B-it-GGUF"
quant: "IQ4_XS"
revision: "main"
preset:
ctx-size: 131072
ctx-size: 98304
- name: "qwen3-5-9b-iq4-xs"
model_id: "unsloth/Qwen3.5-9B-GGUF"
quant: "IQ4_XS"
revision: "main"
preset:
ctx-size: 131072
ctx-size: 98304
- name: "qwen3-5-9b-q8-0"
model_id: "unsloth/Qwen3.5-9B-GGUF"
quant: "Q8_0"
revision: "main"
preset:
ctx-size: 131072
ctx-size: 98304
- name: "qwen3-5-27b-mtp-iq4-xs"
model_id: "unsloth/Qwen3.5-27B-MTP-GGUF"
quant: "IQ4_XS"
revision: "main"
preset:
ctx-size: 131072
ctx-size: 98304
- name: "qwen3-5-35b-a3b-ud-iq4-xs"
model_id: "unsloth/Qwen3.5-35B-A3B-GGUF"
quant: "UD-IQ4_XS"
revision: "main"
preset:
ctx-size: 131072
ctx-size: 98304
- name: "qwen3-5-35b-a3b-q4-k-m"
model_id: "unsloth/Qwen3.5-35B-A3B-GGUF"
quant: "Q4_K_M"
revision: "main"
preset:
ctx-size: 131072
ctx-size: 98304
- name: "qwen3-6-27b-mtp-q4-0"
model_id: "unsloth/Qwen3.6-27B-MTP-GGUF"
quant: "Q4_0"
revision: "main"
preset:
ctx-size: 131072
ctx-size: 98304
- name: "qwen3-6-27b-mtp-ud-q4-0-k-xl"
model_id: "unsloth/Qwen3.6-27B-MTP-GGUF"
quant: "UD-Q4_K_XL"
revision: "main"
preset:
ctx-size: 131072
ctx-size: 98304
- name: "qwen3-6-27b-mtp-ud-q4-xl"
model_id: "unsloth/Qwen3.6-27B-MTP-GGUF"
quant: "UD-Q4_K_XL"
revision: "main"
preset:
ctx-size: 131072
ctx-size: 98304
- name: "qwen3-6-35b-a3b-mtp-ud-iq4-xs"
model_id: "unsloth/Qwen3.6-35B-A3B-MTP-GGUF"
quant: "UD-IQ4_XS"
revision: "main"
preset:
ctx-size: 131072
ctx-size: 98304
- name: "qwen3-6-35b-a3b-mtp-ud-q4-m"
model_id: "unsloth/Qwen3.6-35B-A3B-MTP-GGUF"
quant: "UD-Q4_K_M"
revision: "main"
preset:
ctx-size: 131072
ctx-size: 98304
- name: "qwen3-6-35b-a3b-ud-q4-k-m"
model_id: "unsloth/Qwen3.6-35B-A3B-GGUF"
quant: "UD-Q4_K_M"
revision: "main"
preset:
ctx-size: 131072
ctx-size: 98304
- name: "qwen3-6-35b-a3b-claude47-distilled-iq4-xs"
model_id: "lordx64/Qwen3.6-35B-A3B-Claude-4.7-Opus-Reasoning-Distilled-IQ4_XS-GGUF"
quant: "IQ4_XS"
revision: "main"
preset:
ctx-size: 131072
ctx-size: 98304
- name: "ministral-3-14b-instruct-iq4-xs"
model_id: "unsloth/Ministral-3-14B-Instruct-2512-GGUF"
quant: "IQ4_XS"
revision: "main"
preset:
ctx-size: 131072
ctx-size: 98304
- name: "granite-4-1-30b-iq4-xs"
model_id: "unsloth/granite-4.1-30b-GGUF"
quant: "IQ4_XS"
revision: "main"
preset:
ctx-size: 131072
ctx-size: 98304
- name: "devstral-small-2-24b-instruct-iq4-xs"
model_id: "unsloth/Devstral-Small-2-24B-Instruct-2512-GGUF"
quant: "IQ4_XS"
@@ -239,7 +239,7 @@ llama_server_argv_extra:
"-t",
10,
"-np",
1,
-1,
"-b",
1024,
"-ub",
@@ -257,7 +257,7 @@ llama_server_argv_extra:
"-dev",
"Vulkan1,Vulkan2",
"-ts",
"8,12",
"12,16",
"-fit",
"off",
"-mg",
@@ -265,8 +265,13 @@ llama_server_argv_extra:
"--mmap",
]
auto_suspend_enabled: true
auto_suspend_check_interval: 1min
auto_suspend_idle_timeout_cycles: 2
auto_suspend_cpu_idle_threshold: 90.0
auto_suspend_gpu_util_threshold: 10.0
# # Optional global model preset options applied under [*] in models.ini.
# # Keys map to llama.cpp CLI args without leading dashes, short args, or LLAMA_ARG_* env names.
# llama_server_preset_global:
# ctx-size: 131072
# ctx-size: 98304
# n-gpu-layers: all