michael/AI-Profile-Router
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Update llama.cpp to b10930 and migrate model loading option

Browse Source
This commit is contained in:
Mikei386
2026-09-12 20:41:05 +02:00
parent 6c00b00add
commit 2415b27160
9 changed files with 122 additions and 28 deletions
Download Patch File Download Diff File Expand all files Collapse all files
platform/profiles/profile-ultra.conf
+1 -1
View File
@@ -3,4 +3,4 @@ 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 --cache-prompt --cache-reuse 256 --cache-ram 8192 --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
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 --cache-prompt --cache-reuse 256 --cache-ram 8192 --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 --load-mode none --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