Configure HauhauCS FastMTP 32K draft head, reasoning parameters, and non-thinking mode

scripts/start-server.sh

@@ -1,6 +1,7 @@
 #!/bin/bash
 # llama-server launcher for Qwen3.8-27B on 3x Turing GPUs (RTX 2060 12GB + 2x CMP 50HX 10GB)
 # Built with NVIDIA NCCL for hardware-accelerated multi-GPU tensor parallelism.
+# Accelerated with HauhauCS FastMTP 32K draft sidecar and official thinking parameters.
 export LD_LIBRARY_PATH=/opt/llama.cpp-xrip/build-nccl/bin:/opt/minicpm-venv/lib/python3.13/site-packages/nvidia/nccl/lib:/lib/x86_64-linux-gnu
 
 # Low-Latency NCCL & CUDA Driver Pipeline Optimizations
@@ -13,14 +14,28 @@ export NCCL_PROTO=SIMPLE
 
 exec /opt/llama.cpp-xrip/build-nccl/bin/llama-server \
   -m /opt/models/gguf/Qwen3.8-27B-Uncensored-HauhauCS-Aggressive-Q4_K_P.gguf \
+  --spec-draft-model /opt/models/gguf/Qwen3.8-27B-Uncensored-HauhauCS-Aggressive-FastMTP-32K.gguf \
+  --spec-draft-device CUDA2 \
+  --spec-draft-ngl all \
+  --spec-type draft-mtp \
+  --spec-draft-n-max 3 \
+  --spec-draft-p-min 0 \
   --mmproj /opt/models/gguf/mmproj-Qwen3.8-27B-Uncensored-f16.gguf \
   --mmproj-device CUDA2 \
   --image-min-tokens 1024 \
-  --spec-type draft-mtp \
-  --spec-draft-n-max 2 \
+  --temp 1.0 \
+  --top-k 20 \
+  --top-p 0.95 \
+  --min-p 0 \
+  --presence-penalty 0 \
+  --repeat-penalty 1.0 \
+  --reasoning on \
+  --reasoning-effort xhigh \
+  --reasoning-preserve \
+  --reasoning-format deepseek \
   --numa split \
   -ngl 99 \
-  -c 262144 \
+  -c 204800 \
   --parallel 1 \
   --slot-save-path /var/cache/llama-slots \
   --cache-ram 16384 \