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

Limit prompt cache reuse to text-only profiles

Browse Source
This commit is contained in:
Mikei386
2026-08-25 19:26:48 +02:00
parent d921dfaf69
commit c25e57af57
6 changed files with 22 additions and 16 deletions
Download Patch File Download Diff File Expand all files Collapse all files
platform/profiles/profile-fast.conf
+1 -1
View File
@@ -3,4 +3,4 @@ Description=Local AI llama.cpp - Qwen Fast 76.8K MTP2 with CPU Vision
[Service]
ExecStart=
ExecStart=/opt/mike-ai/llama.cpp-nvfp4/build/bin/llama-server --model /opt/mike-ai/models/qwen3.8-27b-iq4-mix/Qwen3.8-27B-IQ4-MIX.gguf --mmproj /opt/mike-ai/models/qwen3.8-27b-nvfp4/mmproj-BF16.gguf --no-mmproj-offload --alias qwen38-27b-iq4mix-76k-mtp2-vision --ctx-size 76800 --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 --split-mode none --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-nvfp4/build/bin/llama-server --model /opt/mike-ai/models/qwen3.8-27b-iq4-mix/Qwen3.8-27B-IQ4-MIX.gguf --mmproj /opt/mike-ai/models/qwen3.8-27b-nvfp4/mmproj-BF16.gguf --no-mmproj-offload --alias qwen38-27b-iq4mix-76k-mtp2-vision --ctx-size 76800 --flash-attn on --cache-type-k q4_0 --cache-type-v q4_0 --cache-prompt --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 --split-mode none --spec-type draft-mtp --spec-draft-n-max 2 --spec-draft-type-k f16 --spec-draft-type-v f16