Define four-profile production matrix with Medium default

2026-08-22 11:30:38 +02:00
parent 977f8f5c76
commit 41b9c17f0f
33 changed files with 237 additions and 160 deletions
@@ -0,0 +1,6 @@
+[Unit]
+Description=Legacy native Qwen Ultra 256K profile (Docker is the production path)
+
+[Service]
+ExecStart=
+ExecStart=/opt/mike-ai/llama.cpp/build/bin/llama-server --model /opt/mike-ai/models/qwen3.8-27b-iq4-xs-pure/qwen3.8-27b-IQ4_XS-pure.gguf --alias qwen-ultra --ctx-size 262144 --flash-attn on --cache-type-k q4_0 --cache-type-v q4_0 --threads 6 --threads-batch 6 --batch-size 64 --ubatch-size 32 --parallel 1 --jinja --reasoning auto --host 127.0.0.1 --port 8080 --metrics --fit off --n-gpu-layers all --no-mmap --temperature 0.2 --top-p 0.8 --top-k 20 --device CUDA0,CUDA1 --main-gpu 0 --split-mode layer --tensor-split 80,20 --spec-type draft-mtp --spec-draft-n-max 2 --spec-draft-type-k f16 --spec-draft-type-v f16