Enable DFlash speculative decoding, remove mlock

- Add --spec-type draft-dflash (was missing, DFlash was inactive)
- Change --load-mode from mlock to none (RLIMIT_MEMLOCK too small for 2.7GB)
- Increase validation max_tokens from 256 to 1024 with complex ML prompt
- Baseline: 18.76 tok/s (was 7.62 tok/s without DFlash)

scripts/llama-server.service

@@ -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-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 mlock
+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
 

scripts/serve-llamacpp-dflash.sh

@@ -26,6 +26,7 @@ echo ""
 exec "${SERVER_BIN}" \
     --hf-repo "${TARGET_REPO}" \
     --spec-draft-hf "${DRAFT_REPO}" \
+    --spec-type draft-dflash \
     --spec-draft-n-max "${DRAFT_N_MAX}" \
     --device ROCm0 \
     --spec-draft-device ROCm0 \
@@ -38,4 +39,4 @@ exec "${SERVER_BIN}" \
     --port "${PORT}" \
     --host "0.0.0.0" \
     --threads 16 \
-    --load-mode mlock
+    --load-mode none

scripts/validate.sh

@@ -5,7 +5,7 @@ set -euo pipefail
 
 PORT="${LLAMA_PORT:-8080}"
 HOST="${LLAMA_HOST:-127.0.0.1}"
-MAX_TOKENS="${MAX_TOKENS:-256}"
+MAX_TOKENS="${MAX_TOKENS:-1024}"
 
 echo "=== llama.cpp Validation Test ==="
 echo "Target: http://${HOST}:${PORT}"
@@ -36,7 +36,7 @@ RESPONSE=$(curl -s \
     -H "Content-Type: application/json" \
     -d "{
         \"messages\": [
-            {\"role\": \"user\", \"content\": \"What is 2+2? Answer in one sentence.\"}
+            {\"role\": \"user\", \"content\": \"Explain the difference between supervised, unsupervised, and reinforcement learning in machine learning. For each type, provide a concrete real-world example, describe the training process, and discuss the advantages and limitations. Then compare them across three dimensions: data requirements, interpretability of results, and computational cost. Finally, describe a hybrid scenario where combining two of these approaches would outperform using either alone.\"}
         ],
         \"max_tokens\": ${MAX_TOKENS},
         \"temperature\": 0.7,