Enable llama.cpp builds, release management and reference model auto-fit

This commit is contained in:
Mikei386
2026-09-28 16:45:24 +02:00
parent 5fb732469a
commit ba524b0a70
13 changed files with 411 additions and 20 deletions
+4 -3
View File
@@ -1,7 +1,8 @@
FROM python:3.13-slim-bookworm
FROM nvidia/cuda:12.8.1-devel-ubuntu24.04
RUN apt-get update && DEBIAN_FRONTEND=noninteractive apt-get install -y --no-install-recommends python3 git cmake g++ make ca-certificates libssl-dev && rm -rf /var/lib/apt/lists/*
WORKDIR /app
COPY server.py catalog.py auth.py collect_hardware.py demo.py /app/
COPY index.html app.js studio.js catalog-ui.js style.css login.html login.js access-ui.js network-ui.js /app/
COPY server.py runtime.py catalog.py auth.py collect_hardware.py demo.py /app/
COPY index.html app.js studio.js runtime-ui.js catalog-ui.js style.css login.html login.js access-ui.js network-ui.js /app/
COPY network/__init__.py network/client.py network/config.py network/rpc.py /app/network/
ENV PYTHONDONTWRITEBYTECODE=1 PYTHONUNBUFFERED=1 HOME=/tmp \
DECK_BIND_HOST=0.0.0.0 DECK_STATE_DIR=/var/lib/deck \
+10 -5
View File
@@ -14,7 +14,7 @@ import urllib.request
ROOT = Path(__file__).resolve().parent.parent
LABEL = 'de.casaderoll.athena-deck.standalone'
FILES = ['catalog.py','catalog-ui.js','server.py','auth.py','collect_hardware.py','demo.py','index.html','app.js','studio.js','style.css','login.html','login.js','access-ui.js','network-ui.js','network/__init__.py','network/client.py','network/config.py','network/rpc.py','deploy/Dockerfile']
FILES = ['runtime.py','runtime-ui.js','catalog.py','catalog-ui.js','server.py','auth.py','collect_hardware.py','demo.py','index.html','app.js','studio.js','style.css','login.html','login.js','access-ui.js','network-ui.js','network/__init__.py','network/client.py','network/config.py','network/rpc.py','deploy/Dockerfile']
def run(*args, check=True, interactive=False):
@@ -93,7 +93,7 @@ def launch(config):
base=Path(config['base'])
args=['docker','run','-d','--name',config['name'],'--label',LABEL+'='+str(base),
'--restart','unless-stopped','--read-only','--cap-drop','ALL','--security-opt','no-new-privileges:true',
'--pids-limit','128','--memory','512m','--cpus','1', '--tmpfs','/tmp:rw,nosuid,nodev,size=16m',
'--pids-limit','128','--memory','8g','--cpus','2', '--tmpfs','/tmp:rw,nosuid,nodev,size=256m',
'-v',str(base/'state')+':/var/lib/deck:rw','-e','DECK_ALLOWED_HOSTS=127.0.0.1:'+str(config['port'])+',localhost:'+str(config['port']),
'-p','127.0.0.1:'+str(config['port'])+':8108',
'--health-cmd', 'python3 -c "import urllib.request,json; assert json.load(urllib.request.urlopen(\'http://127.0.0.1:8108/api/v1/auth/status\',timeout=3))[\'initialized\']"',
@@ -103,7 +103,12 @@ def launch(config):
# Explicit isolated development bootstrap, reachable only through host loopback/SSH.
args += ['-e','DECK_REQUIRE_SETUP=0']
if config['gpu_telemetry']:
args += ['--gpus','all','-e','NVIDIA_DRIVER_CAPABILITIES=utility']
args += ['--gpus','all','-e','NVIDIA_DRIVER_CAPABILITIES=compute,utility']
if config.get('reference_models'):
for folder,filename in [('qwen3.8-27b-iq4-mix','Qwen3.8-27B-IQ4-MIX.gguf'),('qwen3.8-27b-iq4-xs-pure','qwen3.8-27b-IQ4_XS-pure.gguf'),('qwen3.8-27b-abliterated','Qwen3.8-27B-ABLITERATED-Q4_K_M.gguf')]:
source=Path('/data/models')/folder/filename
if not source.is_file():raise RuntimeError('Referenzmodell fehlt; keine Ersatzpfade.')
args+=['--mount','type=bind,src='+str(source)+',dst=/reference-models/'+filename+',readonly']
args.append(config['image'])
run(*args)
@@ -181,7 +186,7 @@ def update(base, rollback=False):
backup_name=config['name']+'-previous'
if inspect(backup_name):raise RuntimeError('Rückfall-Containername belegt. Keine Änderung ausgeführt.')
stamp=str(time.time_ns())
shutil.copytree(base/'state',base/'backups'/stamp,ignore=shutil.ignore_patterns('models'))
shutil.copytree(base/'state',base/'backups'/stamp,ignore=shutil.ignore_patterns('models','runtime','runtime-verification'))
was_running=previous['State']['Running']
if was_running:run('docker','stop','--time','15',config['name'])
run('docker','rename',config['name'],backup_name)
@@ -206,7 +211,7 @@ def main():
parser.add_argument('--directory',type=Path,default=Path('/opt/athena-deck-standalone'))
parser.add_argument('--name',default='athena-deck-standalone')
parser.add_argument('--port',type=int,default=8110)
parser.add_argument('--gpu-telemetry',action='store_true',help='Vorhandenes NVIDIA Container Toolkit nur für Messwerte nutzen; installiert keine Treiber.')
parser.add_argument('--gpu-telemetry',action='store_true',help='Vorhandenes NVIDIA Container Toolkit für Messwerte und Fit-Prüfung nutzen; installiert keine Treiber.')
args=parser.parse_args()
import re
if not re.fullmatch(r'athena-deck-[a-z0-9-]{1,40}',args.name):