Add FASTGREEDY mode to serve script: reasoning off + argmax fastpath on for fast-greedy bench

FASTGREEDY=1 flips the serve script to the card's default profile:
- reasoning off (no logit budget overhead)
- LLAMA_TARGET_GREEDY_ARGMAX_FASTPATH=1 (exact-Q8 GPU argmax)
- deterministic sampler (temp 0, top_p 1, top_k 0, min_p 0)

This mirrors the card's 'fast greedy (default)' benchmark config.
Production (FASTGREEDY=0) unchanged.

scripts/frank-default-large.env

@@ -81,3 +81,8 @@ SPEC_DRAFT_P_SPLIT=0.10
 # message.reasoning_content, matching the retired v3 service) with
 # --reasoning-budget -1 (unrestricted) and chat_template_kwargs
 # preserve_thinking=true (preserve thinking tokens across turns).
+#
+# For fast-greedy bench: comment out the --reasoning on line in serve script
+# and set FASTGREEDY=1 in env (see serve script FASTGREEDY section).
+# FASTGREEDY=1 flips to: reasoning off, argmax fastpath=1, sampling defaults.
+# FASTGREEDY=0 (default) uses the production values above.

scripts/serve-frank-large.sh

@@ -100,7 +100,17 @@ export GGML_CUDA_GRAPH_OPT=0
 # path rejects. Production chat therefore forces it to 0. This does NOT
 # affect the Kairic Edge IU4 lane (prompt/verification route via
 # --kairic-edge) nor the MTP draft fast path below.
-export LLAMA_TARGET_GREEDY_ARGMAX_FASTPATH=0
+# FASTGREEDY env var (0 = production chat, 1 = fast-greedy bench from
+# card's default profile). When FASTGREEDY=1: reasoning off, argmax
+# fastpath active, deterministic sampler. Compatible mode (KAIRIC_EDGE
+# compatibility mode) only disables the target greedy argmax fast path;
+# reasoning is disabled separately.
+FASTGREEDY="${FASTGREEDY:-0}"
+if [ "$FASTGREEDY" = "1" ]; then
+    export LLAMA_TARGET_GREEDY_ARGMAX_FASTPATH=1
+else
+    export LLAMA_TARGET_GREEDY_ARGMAX_FASTPATH=0
+fi
 export LLAMA_MTP_CPU_ARGMAX_FASTPATH=1
 export PROMPTFORGE_TARGET_ONLY=0
 export PROMPTFORGE_MODE=iu4_ffn
@@ -125,6 +135,24 @@ export PROMPTFORGE_ENABLE_SMALLM_GDN_OUTPUT_IU4=0
 export PROMPTFORGE_ENABLE_IU4_DECODE_M2_M5=0
 export PROMPTFORGE_OUTPUT_K8_STRICT_GREEDY=0
 
+# Sampling & reasoning defaults — production (FASTGREEDY=0) vs fast-greedy
+# (FASTGREEDY=1). Fast greedy uses the card's default deterministic sampler
+# with argmax fastpath active; production uses Qwen live values with
+# reasoning budget and argmax fastpath off.
+if [ "$FASTGREEDY" = "1" ]; then
+    TEMP=0
+    TOP_P=1.0
+    TOP_K=0
+    MIN_P=0.0
+    REASONING_ARGS=""
+else
+    TEMP=0
+    TOP_P=1.0
+    TOP_K=0
+    MIN_P=0.0
+    REASONING_ARGS="--reasoning on --reasoning-format deepseek --reasoning-budget -1"
+fi
+
 # Pinned runner flags (qualified 262K one-slot profile, native MTP depth
 # 4, deterministic sampler; batch 2048 / ubatch 512 are the runner's
 # qualified sizes and give the fastest measured prefill). Local overrides
@@ -171,11 +199,9 @@ exec "$LLAMA_BIN" \
     --spec-draft-p-min "$SPEC_DRAFT_P_MIN" \
     --spec-draft-p-split "$SPEC_DRAFT_P_SPLIT" \
     --spec-draft-backend-sampling \
-    --temp 0 \
-    --top-p 1.0 \
-    --top-k 0 \
-    --min-p 0.0 \
-    --reasoning on \
-    --reasoning-format deepseek \
-    --reasoning-budget -1 \
+    --temp "$TEMP" \
+    --top-p "$TOP_P" \
+    --top-k "$TOP_K" \
+    --min-p "$MIN_P" \
+    $REASONING_ARGS \
     --chat-template-kwargs '{"preserve_thinking":"true"}'