Configure DeepSeek reasoning and large-model ubatch sweep

scripts/bench-ubatch-rocmi4.sh

@@ -1,6 +1,6 @@
 #!/usr/bin/env bash
 # bench-ubatch-rocmi4.sh — sweep ubatch size at 8k context on the
-# frank-default-large ROCmI4 embedded-MTP stack (dankclaw, gfx1151).
+# frank-default-large ROCmFPX standalone-MTP stack (dankclaw, gfx1151).
 #
 # Boots one llama-server instance per ubatch on a scratch port with a fixed
 # -b and -c 8192, runs a standardized ~75%-of-ctx prose workload, and reads
@@ -26,21 +26,23 @@ if [[ -f "$ENV_FILE" ]]; then
 fi
 
 # --- sweep parameters -------------------------------------------------------
-: "${UBATCH_MIN:=512}"
-: "${UBATCH_MAX:=4096}"
-: "${UBATCH_STEP:=512}"
+: "${UBATCH_MIN:=256}"
+: "${UBATCH_MAX:=6144}"
+: "${UBATCH_STEP:=256}"
+: "${UBATCH_VALUES:=256 512 768 1024 1280 1536 2048 3072 4096 5120 6144}"
 : "${CTX:=8192}"                 # 8k contexts
 : "${BENCH_BATCH:=$CTX}"         # fixed batch = ctx, so the full 8k prompt fits
 : "${OUT_TOKENS:=256}"
 : "${RUNS:=3}"                   # decode runs per ubatch
 : "${PORT_BASE:=7894}"           # scratch ports 7894..
-: "${STOPSVC:=0}"                # stop/restart the live unit for a clean GPU
+: "${STOPSVC:=1}"                # stop/restart the live unit for a clean GPU
 
 # --- resolved paths (fall back to serve-script defaults) --------------------
-: "${LLAMA_BIN:=/home/dank/rocmi4-qwen38/ROCmFPX/build-rocmi4-w4a4/bin/llama-server}"
-: "${MODEL_DIR:=/home/dank/models/eemin-Qwen3.8-27B-ROCMI4-MTP}"
-: "${MODEL_FILE:=Qwen3.8-27B-Q4_0_ROCMI4.gguf}"
-: "${MMPROJ_FILE:=mmproj-BF16.gguf}"
+: "${LLAMA_BIN:=/home/dank/ciru-qwen38/ROCmFPX/build-promptforge/bin/llama-server}"
+: "${MODEL_DIR:=/home/dank/models/kingjones-Qwen3.8-27B-STRIX-MTP}"
+: "${MODEL_FILE:=Qwen3.8-27B-Uncensored-Q6_0_ROCMFPX_AGENT.gguf}"
+: "${MTP_DRAFT_FILE:=$MODEL_DIR/mtp-Qwen3.8-27B-Q4_0.gguf}"
+: "${MMPROJ_FILE:=mmproj-Qwen3.8-27B-Q8_0.gguf}"
 : "${CHAT_TEMPLATE_FILE:=$SCRIPT_DIR/chat-template.jinja}"
 : "${ALIAS:=frank-default-large}"
 : "${HSA_OVERRIDE_GFX_VERSION:=11.5.1}"
@@ -114,7 +116,7 @@ run_one() {
         --model "$MODEL" \
         "${MMPROJ_ARGS[@]}" \
         --chat-template-file "$CHAT_TEMPLATE_FILE" \
-        --chat-template-kwargs '{"enable_thinking":true,"preserve_thinking":true}' \
+        --chat-template-kwargs '{"enable_thinking":true,"preserve_thinking":true,"preserve_reasoning":true}' \
         --alias bench-ubatch \
         --host 127.0.0.1 --port "$port" \
         -dev ROCm0 -ngl 999 -np 1 \
@@ -122,14 +124,14 @@ run_one() {
         -c "$CTX" -b "$BENCH_BATCH" -ub "$ubatch" \
         -fa on -ctk f16 -ctv f16 -ctxcp 16 \
         --cache-ram 8192 --cache-prompt --metrics --no-mmap \
-        --spec-type draft-mtp --spec-mtp-strict-qwen \
-        --spec-draft-device ROCm0 --spec-draft-ngl all \
+        --spec-type draft-mtp --model-draft "$MTP_DRAFT_FILE" \
+        --spec-draft-device ROCm0 --spec-draft-ngl 999 \
         --spec-draft-type-k f16 --spec-draft-type-v f16 \
         --spec-draft-n-max "$MTP_N_MAX" --spec-draft-n-min 0 \
         --spec-draft-p-min "$MTP_P_MIN" \
         --spec-draft-backend-sampling \
         --temp 0.7 --top-p 0.95 \
-        --reasoning on --reasoning-format deepseek --reasoning-budget -1 \
+        --reasoning "$REASONING" --reasoning-format "$REASONING_FORMAT" --reasoning-budget -1 \
         -lv 4 >>"$log" 2>&1 &
     local pid=$!
     wait_health "$pid" "$port" || { tail -30 "$log"; return 2; }
@@ -207,7 +209,7 @@ main() {
     stop_live_service
     local idx=0 ubatch port
     printf "%-10s %-14s %-10s\n" "UBATCH" "PREFILL" "GEN_TPS"
-    for ubatch in $(seq "$UBATCH_MIN" "$UBATCH_STEP" "$UBATCH_MAX"); do
+    for ubatch in $UBATCH_VALUES; do
         port=$((PORT_BASE + idx))
         run_one "$ubatch" "$port" "$OUT_TOKENS" "$RUNS"
         idx=$((idx + 1))

scripts/frank-default-large.env

@@ -22,8 +22,9 @@ MTP_DRAFT_FILE=$MODEL_DIR/mtp-Qwen3.8-27B-Q4_0.gguf
 MMPROJ_FILE=mmproj-Qwen3.8-27B-Q8_0.gguf
 
 # Qwen-Sharp chat template (tracked in the repo, staged on the host). The Sharp
-# template drives thinking on by default (medium effort) and produces the
-# peg-native + deepseek chat/reasoning shape the Pi agent expects.
+# template drives thinking on by default (medium effort); the server emits
+# reasoning in DeepSeek format so clients receive reasoning_content separately
+# instead of literal <think> tags in content.
 CHAT_TEMPLATE_FILE=/home/dank/serverAppConfigs/scripts/chat-template.jinja
 CHAT_TEMPLATE_KWARGS='{"enable_thinking":true,"preserve_thinking":true,"preserve_reasoning":true}'
 
@@ -63,10 +64,10 @@ MIN_P=0.0
 PRESENCE_PENALTY=1.5
 
 # Reasoning on (Sharp template drives it; preserve_thinking + preserve_reasoning
-# keep the reasoning trail in the conversation). reasoning-format none lets the
-# template project the reasoning content into reasoning_content.
+# keep the reasoning trail in the conversation). DeepSeek format projects the
+# reasoning into the API's reasoning_content field instead of content tags.
 REASONING=on
-REASONING_FORMAT=none
+REASONING_FORMAT=deepseek
 
 # Strix Halo unified memory + native gfx1151 detection for this ROCmFPX build.
 HSA_OVERRIDE_GFX_VERSION=11.5.1