Benchmark Dirk Qwen3.8 against production

experiments/dirk-qwen38/run-case.sh

@@ -15,14 +15,16 @@ if [[ $MODE != text && $MODE != vision ]]; then
 fi
 
 MODEL_DIR=${MODEL_DIR:-/data/models/qwen3.8-27b-dirk}
-MODEL=/models/qwen3.8-27b-dirk/Dirk-Qwen3.8-27B-UD-Q4_K_XL.gguf
+MODEL=${MODEL_PATH:-/models/qwen3.8-27b-dirk/Dirk-Qwen3.8-27B-UD-Q4_K_XL.gguf}
+HOST_MODEL_FILE=${HOST_MODEL_FILE:-$MODEL_DIR/Dirk-Qwen3.8-27B-UD-Q4_K_XL.gguf}
+MODEL_ALIAS=${MODEL_ALIAS:-qwen-dirk-test}
 PROJECTOR=/models/qwen3.8-27b-dirk/mmproj-F16.gguf
 IMAGE=${LLAMA_IMAGE:-mike-ai/llama.cpp:local}
 NAME=mike-ai-llama-dirk-test
 RESULT_DIR=${RESULT_DIR:-/data/benchmarks/dirk-qwen38}
 
-[[ -s "$MODEL_DIR/Dirk-Qwen3.8-27B-UD-Q4_K_XL.gguf" ]] || {
-  echo "Dirk model is missing; run download-model.sh first" >&2
+[[ -s "$HOST_MODEL_FILE" ]] || {
+  echo "Model file is missing: $HOST_MODEL_FILE" >&2
   exit 1
 }
 if [[ $MODE == vision && ! -s "$MODEL_DIR/mmproj-F16.gguf" ]]; then
@@ -45,21 +47,23 @@ install -d -m 0755 "$RESULT_DIR"
 
 args=(
   --model "$MODEL"
-  --alias qwen-dirk-test
+  --alias "$MODEL_ALIAS"
   --ctx-size "$CONTEXT"
   --flash-attn on
   --cache-type-k q4_0
   --cache-type-v q4_0
   --cache-prompt
-  --cache-ram 8192
+  --cache-ram 24576
   --threads 6
   --threads-batch 6
-  --batch-size 64
-  --ubatch-size 32
+  --batch-size 2048
+  --ubatch-size 128
   --parallel 1
+  --kv-unified
   --jinja
   --reasoning auto
   --reasoning-budget 8192
+  --reasoning-preserve
   --host 127.0.0.1
   --port 5004
   --metrics
@@ -77,6 +81,7 @@ args=(
   --spec-draft-n-max 3
   --spec-draft-type-k f16
   --spec-draft-type-v f16
+  --spec-draft-p-min 0.05
 )
 
 if [[ $MODE == vision ]]; then
@@ -84,7 +89,7 @@ if [[ $MODE == vision ]]; then
 fi
 
 label="ctx${CONTEXT}-split${SPLIT//,/-}-${MODE}"
-docker run -d --rm \
+docker run -d \
   --name "$NAME" \
   --gpus all \
   --network host \
@@ -102,4 +107,3 @@ docker run -d --rm \
   "$IMAGE" "${args[@]}"
 
 printf 'Started isolated case %s on http://127.0.0.1:5004\n' "$label"
-