Frank
471e963350
- Rewrite validation script with temp files for true parallel curl requests - Both prompts now complete 1024 tokens each (was cutting first short) - Remove ngram-mod from spec pipeline (was -1.2 tok/s regression) - True parallel throughput: 15.68 tok/s across 2 streams
15 lines
620 B
Desktop File
15 lines
620 B
Desktop File
[Unit]
|
|
Description=llama.cpp DFlash+MTP Inference Server (Qwen3.6-27B on ROCm)
|
|
After=network.target
|
|
|
|
[Service]
|
|
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
|
|
Restart=on-failure
|
|
RestartSec=10
|
|
|
|
[Install]
|
|
WantedBy=multi-user.target
|