dank/serverAppConfigs
1
0 Fork 0
Code Issues 4 Pull Requests Actions Packages Projects Releases Wiki Activity

Use --alias frank-default-large, multi-stream validation script

Browse Source 
- Replace --override-kv with --alias for model naming
- Validation script tests 1, 2, 3 parallel streams sequentially
- Model name confirmed: frank-default-large
This commit is contained in:
Frank committed 2026-08-07 17:15:09 -07:00
1 parent 471e963350
commit a5f72627bb
3 files changed
+63 -63
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

scripts/llama-server.service
+1 -1
View File
@@ -6,7 +6,7 @@ After=network.target
Type=simple
User=dank
Group=dank
ExecStart=/home/dank/llama.cpp/build/bin/llama-server --hf-repo unsloth/Qwen3.6-27B-MTP-GGUF:Q8_0 --spec-draft-hf Alittlehammmer/Qwen3.6-27B-DFlash-GGUF-llama.cpp:Q8_0 --spec-type draft-dflash --spec-draft-n-max 16 --device ROCm0 --spec-draft-device ROCm0 --gpu-layers all --fit on --fit-target 512 --parallel 3 --ctx-size 131072 --batch-size 4096 --port 8080 --host 0.0.0.0 --threads 16 --load-mode none
ExecStart=/home/dank/llama.cpp/build/bin/llama-server --hf-repo unsloth/Qwen3.6-27B-MTP-GGUF:Q8_0 --spec-draft-hf Alittlehammmer/Qwen3.6-27B-DFlash-GGUF-llama.cpp:Q8_0 --spec-type draft-dflash --spec-draft-n-max 16 --device ROCm0 --spec-draft-device ROCm0 --gpu-layers all --fit on --fit-target 512 --parallel 3 --ctx-size 131072 --batch-size 4096 --port 8080 --host 0.0.0.0 --threads 16 --alias frank-default-large --load-mode none
Restart=on-failure
RestartSec=10