Switch large service to Kairic Edge v1.2

scripts/frank-default-large.env

@@ -1,26 +1,26 @@
-# Tunables for frank-default-large (charlie12345/ROCmFPX, dankclaw, Strix Halo
-# gfx1151, ROCmI4 embedded MTP).
+# Tunables for frank-default-large (CIRU/Kairic Edge ROCmFPX v1.2, dankclaw,
+# Strix Halo gfx1151).
 #
-# Runtime: charlie12345/ROCmFPX commit c49ebdbd built with
-# -DGGML_HIP_ROCMI4_W4A4=ON against the system ROCm (/opt/rocm-7.2.4, amdclang
-# 22). Serves caf-eemin/Qwen3.8-27B-ROCmI4-MTP-GGUF (Q4_0_ROCMI4, embedded
-# MTP, no separate draft head). Alias frank-default-large, port 7770.
-#
-# This model replaced kingjones777/Qwen3.8-27B-Uncensored-ROCmFP4-STRIX-MTP on
-# 2026-08-25. The old kingjones ROCmFP4 GGUF + standalone MTP Q4_0 draft are
-# retired on this slot.
+# Runtime: ciru-ai/ROCmFPX tag kairic-edge-qwen38-27b-v1.2, commit
+# 205a3e5f40e5542e2f2eb68e3d3f81f918b1d895, built with the pinned gfx1151
+# Prompt Forge / IU4 settings against /opt/rocm. Serves the Kairic Edge
+# authoritative GGUF plus three required .pfs sidecars. Alias
+# frank-default-large, port 7770.
 
 # WARNING: do not name any variable TEMP, HOST, or GPU_MAX_HEAP_SIZE. The ROCm
 # HIP runtime reads those bare env vars (see the 2026-08-13 TEMP incident).
 # llama.cpp reads --host/--port/--temp as CLI flags, never as env vars.
 
-# charlie12345/ROCmFPX build with the ROCmI4 W4A4 path.
-LLAMA_BIN=/home/dank/rocmi4-qwen38/ROCmFPX/build-rocmi4-w4a4/bin/llama-server
+# ciru-ai/ROCmFPX Kairic Edge v1.2 build.
+LLAMA_BIN=/home/dank/ciru-qwen38/ROCmFPX/build-kairic/bin/llama-server
 
-# Model files: embedded-MTP ROCmI4 GGUF + optional BF16 vision projector.
-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
+# Model files: authoritative GGUF plus all required Kairic Edge sidecars.
+MODEL_DIR=/home/dank/models/Kairic-Qwen3.8-27B-IU4-Edge
+MODEL_FILE=Qwen3.8-27B-IU4-Kairic-Edge.gguf
+KAIRIC_FFN_SIDECAR=$MODEL_DIR/Qwen3.8-27B-Kairic-IU4-FFN.pfs
+KAIRIC_GDN_SIDECAR=$MODEL_DIR/Qwen3.8-27B-Kairic-IU4-GDN.pfs
+KAIRIC_GDN_OUTPUT_SIDECAR=$MODEL_DIR/Qwen3.8-27B-Kairic-IU4-GDN-Output.pfs
+KAIRIC_EDGE_COMPATIBILITY_MODE=1
 # No separate MTP draft head: the MTP/NextN head is embedded in the main GGUF,
 # so no --model-draft is passed. Kept for scripts that reference the var.
 MTP_DRAFT_FILE=
@@ -45,32 +45,33 @@ PARALLEL=1
 # Batch/ubatch follow the qualified ROCmI4 W4A4 profile (see the bench in
 # scripts/bench-ubatch-rocmi4.sh for the ubatch sweep on 8k contexts).
 BATCH_SIZE=512
-UBATCH_SIZE=256
+UBATCH_SIZE=512
 NUM_THREADS=16
 THREAD_BATCH=32
 CACHE_TYPE_K=f16
 CACHE_TYPE_V=f16
-CTX_CHECKPOINTS=16
+CTX_CHECKPOINTS=32
 CACHE_RAM=8192
 
 # Embedded-MTP (qwen35 NextN) qualified profile. The head is in the main GGUF,
 # so the draft runs with all layers on ROCm0 (no --model-draft).
 MTP_N_MAX=4
 MTP_N_MIN=0
-MTP_P_MIN=0.60
-SPEC_MTP_STRICT_QWEN=on
-MTP_BACKEND_SAMPLING=on
-SPEC_DRAFT_NGL=all
+MTP_P_MIN=0.0
+MTP_P_SPLIT=0.10
+KAIRIC_EDGE_COMPATIBILITY_MODE=1
 
 # Sampling (Sharp default).
-TEMPERATURE=1.0
+TEMPERATURE=0.7
 TOP_K=20
-TOP_P=0.95
+TOP_P=0.8
+MIN_P=0.0
+PRESENCE_PENALTY=1.5
 
 # Thinking on (Sharp template drives it; reasoning format projects the tar into
 # reasoning_content).
-REASONING=on
-REASONING_FORMAT=deepseek
+REASONING=off
+REASONING_FORMAT=none
 
 # Strix Halo unified memory + native gfx1151 detection for this ROCmFPX build.
 HSA_OVERRIDE_GFX_VERSION=11.5.1

scripts/frank-default-large.service

@@ -1,5 +1,5 @@
 [Unit]
-Description=ROCmFPX llama.cpp Qwen3.8-27B ROCmI4 embedded MTP + Sharp template (dankclaw, frank-default-large)
+Description=Kairic Edge ROCmFPX llama.cpp Qwen3.8-27B IU4 + MTP (dankclaw, frank-default-large)
 After=network-online.target
 Wants=network-online.target
 

scripts/serve-frank-large.sh

@@ -1,24 +1,10 @@
 #!/usr/bin/env bash
-# Serve caf-eemin/Qwen3.8-27B-ROCmI4-MTP-GGUF (Q4_0_ROCMI4, embedded MTP) as
-# frank-default-large via the charlie12345/ROCmFPX llama.cpp runtime
-# (ROCmI4 W4A4) on Dankclaw (Strix Halo gfx1151).
-#
-# Runtime: charlie12345/ROCmFPX pinned at commit
-# c49ebdbd5c9f01ec242369f9e7f7967855f80cba, built with
-# -DGGML_HIP_ROCMI4_W4A4=ON against the system ROCm (/opt/rocm-7.2.4,
-# amdclang 22). The model has an embedded NextN/MTP head in the main GGUF, so
-# a separate draft file is not loaded; the MTP draft runs on ROCm0 with all
-# layers via --spec-draft-ngl all.
-#
-# The qualified MTP profile is strict Qwen MTP (--spec-mtp-strict-qwen) with
-# backend sampling, n_max 16, p_min 0.60 (see the model card and the
-# charlie12345/ROCmFPX ROCMI4 runbook).
-#
-# Tunables come from frank-default-large.env in this directory unless
-# FRANK_LARGE_ENV_FILE overrides that path.
+# Serve Qwen3.8-27B IU4 Kairic Edge v1.2 as frank-default-large.
+# The Kairic runtime requires its authoritative GGUF and all three Prompt Forge
+# sidecars. Compatibility mode is enabled for Qwen's recommended sampling.
 set -euo pipefail
 
-SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
+SCRIPT_DIR="$(cd -- "$(dirname -- "${BASH_SOURCE[0]}")" && pwd)"
 ENV_FILE="${FRANK_LARGE_ENV_FILE:-$SCRIPT_DIR/frank-default-large.env}"
 if [[ -f "$ENV_FILE" ]]; then
     set -a
@@ -27,115 +13,101 @@ if [[ -f "$ENV_FILE" ]]; then
     set +a
 fi
 
-# --- defaults (used when the env file does not set them) -------------------
-: "${LLAMA_BIN:=/home/dank/rocmi4-qwen38/ROCmFPX/build-rocmi4-w4a4/bin/llama-server}"
-: "${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}"
-: "${CHAT_TEMPLATE_FILE:=$SCRIPT_DIR/chat-template.jinja}"
+: "${LLAMA_BIN:=/home/dank/ciru-qwen38/ROCmFPX/build-kairic/bin/llama-server}"
+: "${MODEL_DIR:=/home/dank/models/Kairic-Qwen3.8-27B-IU4-Edge}"
+: "${MODEL_FILE:=Qwen3.8-27B-IU4-Kairic-Edge.gguf}"
+: "${KAIRIC_FFN_SIDECAR:=$MODEL_DIR/Qwen3.8-27B-Kairic-IU4-FFN.pfs}"
+: "${KAIRIC_GDN_SIDECAR:=$MODEL_DIR/Qwen3.8-27B-Kairic-IU4-GDN.pfs}"
+: "${KAIRIC_GDN_OUTPUT_SIDECAR:=$MODEL_DIR/Qwen3.8-27B-Kairic-IU4-GDN-Output.pfs}"
 : "${ALIAS:=frank-default-large}"
 : "${BIND_ADDR:=0.0.0.0}"
 : "${LISTEN_PORT:=7770}"
 : "${CTX_SIZE:=262144}"
 : "${PARALLEL:=1}"
-: "${BATCH_SIZE:=512}"
-: "${UBATCH_SIZE:=256}"
+: "${BATCH_SIZE:=2048}"
+: "${UBATCH_SIZE:=512}"
 : "${NUM_THREADS:=16}"
 : "${THREAD_BATCH:=32}"
 : "${CACHE_TYPE_K:=f16}"
 : "${CACHE_TYPE_V:=f16}"
-: "${CTX_CHECKPOINTS:=16}"
+: "${CTX_CHECKPOINTS:=32}"
 : "${CACHE_RAM:=8192}"
-# Embedded-MTP (qwen35 NextN) qualified profile. The MTP head lives in the main
-# GGUF, so no standalone draft file is referenced; the draft runs on ROCm0 with all layers.
-: "${MTP_N_MAX:=16}"
+: "${MTP_N_MAX:=4}"
 : "${MTP_N_MIN:=0}"
-: "${MTP_P_MIN:=0.60}"
-: "${SPEC_MTP_STRICT_QWEN:=on}"
-: "${MTP_BACKEND_SAMPLING:=on}"
-: "${SPEC_DRAFT_NGL:=all}"
-: "${TEMPERATURE:=1.0}"
+: "${MTP_P_MIN:=0.0}"
+: "${MTP_P_SPLIT:=0.10}"
+: "${TEMPERATURE:=0.7}"
 : "${TOP_K:=20}"
-: "${TOP_P:=0.95}"
-: "${REASONING:=on}"
-: "${REASONING_FORMAT:=deepseek}"
-: "${CHAT_TEMPLATE_KWARGS:={}}"
-: "${VERBOSITY:=4}"
-# Strix Halo unified memory + native gfx1151 detection for this ROCmFPX build.
+: "${TOP_P:=0.8}"
+: "${MIN_P:=0.0}"
+: "${PRESENCE_PENALTY:=1.5}"
+: "${REASONING:=off}"
+: "${REASONING_FORMAT:=none}"
+: "${KAIRIC_EDGE_COMPATIBILITY_MODE:=1}"
 : "${HSA_OVERRIDE_GFX_VERSION:=11.5.1}"
-: "${GGML_HIP_ENABLE_UNIFIED_MEMORY:=1}"
 
 MODEL="$MODEL_DIR/$MODEL_FILE"
-MMPROJ="$MODEL_DIR/$MMPROJ_FILE"
-
-# Optional vision projector: load it only if the file exists.
-MMPROJ_ARGS=()
-if [[ -f "$MMPROJ" ]]; then
-    MMPROJ_ARGS=(--mmproj "$MMPROJ")
-fi
-
-for f in "$MODEL" "$CHAT_TEMPLATE_FILE"; do
-    if [[ ! -f "$f" ]]; then
-        echo "missing required file: $f" >&2
+for f in "$LLAMA_BIN" "$MODEL" "$KAIRIC_FFN_SIDECAR" "$KAIRIC_GDN_SIDECAR" "$KAIRIC_GDN_OUTPUT_SIDECAR"; do
+    if [[ ! -r "$f" ]]; then
+        echo "missing or unreadable required artifact: $f" >&2
         exit 1
     fi
 done
 if [[ ! -x "$LLAMA_BIN" ]]; then
-    echo "missing llama-server binary: $LLAMA_BIN" >&2
+    echo "missing executable runtime: $LLAMA_BIN" >&2
+    exit 1
+fi
+if [[ "$KAIRIC_EDGE_COMPATIBILITY_MODE" != 1 ]]; then
+    echo "KAIRIC_EDGE_COMPATIBILITY_MODE must be 1 for this deployment" >&2
     exit 1
 fi
 
-# Any leftover PromptForge env lanes from the previous (kingjones/v3) runtime
-# must stay off; this slot now runs the plain strict-MTP draft-mtp path.
-unset PROMPTFORGE_SIDECAR PROMPTFORGE_GDN_SIDECAR PROMPTFORGE_MTP_OUTPUT_K8_PROXY || true
-unset PROMPTFORGE_MODE PROMPTFORGE_ENABLE_SMALLM_W8 || true
-unset PROMPTFORGE_MTP_OUTPUT_K8 PROMPTFORGE_MTP_OUTPUT_K8_VALIDATE || true
-unset PROMPTFORGE_IU4_SIDECAR PROMPTFORGE_GDN_IU4_SIDECAR || true
-unset PROMPTFORGE_ENABLE_NGRAM_MOD PROMPTFORGE_ENABLE_NGRAM_M65_IU4 || true
-unset LLAMA_MTP_CPU_ARGMAX_FASTPATH LLAMA_MTP_BACKEND_GREEDY || true
+SERVER_DIR="$(cd -- "$(dirname -- "$LLAMA_BIN")" && pwd)"
+ROCM_PATH="${ROCM_PATH:-/opt/rocm}"
+LIBRARY_PATH="$SERVER_DIR:$ROCM_PATH/lib:$ROCM_PATH/lib/rocm_sysdeps/lib:$ROCM_PATH/lib/llvm/lib:$ROCM_PATH/llvm/lib${LD_LIBRARY_PATH:+:$LD_LIBRARY_PATH}"
 
-# Strix Halo unified memory + native gfx1151 detection for this ROCmFPX build.
-export HSA_OVERRIDE_GFX_VERSION
-export GGML_HIP_ENABLE_UNIFIED_MEMORY
-
-exec "$LLAMA_BIN" \
-    --model "$MODEL" \
-    "${MMPROJ_ARGS[@]}" \
-    --chat-template-file "$CHAT_TEMPLATE_FILE" \
-    --chat-template-kwargs "$CHAT_TEMPLATE_KWARGS" \
-    --alias "$ALIAS" \
-    --host "$BIND_ADDR" \
-    --port "$LISTEN_PORT" \
-    -dev ROCm0 \
-    -ngl 999 \
-    -np "$PARALLEL" \
-    -t "$NUM_THREADS" \
-    -tb "$THREAD_BATCH" \
-    -c "$CTX_SIZE" \
-    -b "$BATCH_SIZE" \
-    -ub "$UBATCH_SIZE" \
-    -fa on \
-    -ctk "$CACHE_TYPE_K" \
-    -ctv "$CACHE_TYPE_V" \
-    -ctxcp "$CTX_CHECKPOINTS" \
-    --cache-ram "$CACHE_RAM" \
-    --cache-prompt \
-    --metrics \
-    --no-mmap \
-    --spec-type draft-mtp \
-    ${SPEC_MTP_STRICT_QWEN:+--spec-mtp-strict-qwen} \
-    --spec-draft-device ROCm0 \
-    --spec-draft-ngl "$SPEC_DRAFT_NGL" \
-    --spec-draft-type-k "$CACHE_TYPE_K" \
-    --spec-draft-type-v "$CACHE_TYPE_V" \
-    --spec-draft-n-max "$MTP_N_MAX" \
-    --spec-draft-n-min "$MTP_N_MIN" \
-    --spec-draft-p-min "$MTP_P_MIN" \
-    ${MTP_BACKEND_SAMPLING:+--spec-draft-backend-sampling} \
-    --temp "$TEMPERATURE" \
-    --top-k "$TOP_K" \
-    --top-p "$TOP_P" \
-    --reasoning "$REASONING" \
-    --reasoning-format "$REASONING_FORMAT" \
-    --reasoning-budget -1 \
-    -lv "$VERBOSITY"
+exec /usr/bin/env \
+    ROCM_PATH="$ROCM_PATH" \
+    HIP_VISIBLE_DEVICES=0 \
+    HSA_OVERRIDE_GFX_VERSION="$HSA_OVERRIDE_GFX_VERSION" \
+    LD_LIBRARY_PATH="$LIBRARY_PATH" \
+    GGML_CUDA_GRAPH_OPT=0 \
+    LLAMA_TARGET_GREEDY_ARGMAX_FASTPATH=0 \
+    LLAMA_MTP_CPU_ARGMAX_FASTPATH=1 \
+    PROMPTFORGE_TARGET_ONLY=0 \
+    PROMPTFORGE_MODE=iu4_ffn \
+    PROMPTFORGE_IU4_SIDECAR="$KAIRIC_FFN_SIDECAR" \
+    PROMPTFORGE_SIDECAR="$KAIRIC_FFN_SIDECAR" \
+    PROMPTFORGE_IU4_HADAMARD=1 \
+    PROMPTFORGE_IU4_SEGMENTED=0 \
+    PROMPTFORGE_ENABLE_FFN_KEEPERS=0 \
+    PROMPTFORGE_FFN_KEEPERS=late6 \
+    PROMPTFORGE_ENABLE_GDN=1 \
+    PROMPTFORGE_ENABLE_GDN_W8=0 \
+    PROMPTFORGE_GDN_SIDECAR_OVERRIDE="$KAIRIC_GDN_SIDECAR" \
+    PROMPTFORGE_GDN_SIDECAR="$KAIRIC_GDN_SIDECAR" \
+    PROMPTFORGE_GDN_IU4_HADAMARD=1 \
+    PROMPTFORGE_ENABLE_GDN_KEEPERS=0 \
+    PROMPTFORGE_ENABLE_GDN_OUTPUT=1 \
+    PROMPTFORGE_GDN_OUTPUT_SIDECAR="$KAIRIC_GDN_OUTPUT_SIDECAR" \
+    PROMPTFORGE_GDN_OUTPUT_KEEPERS=v3_lateq6 \
+    PROMPTFORGE_ENABLE_SMALLM_IU4=1 \
+    PROMPTFORGE_ENABLE_SMALLM_GDN_IU4=1 \
+    PROMPTFORGE_ENABLE_SMALLM_GDN_OUTPUT_IU4=0 \
+    PROMPTFORGE_ENABLE_IU4_DECODE_M2_M5=0 \
+    PROMPTFORGE_OUTPUT_K8_STRICT_GREEDY=0 \
+    "$LLAMA_BIN" -m "$MODEL" --alias "$ALIAS" \
+    --host "$BIND_ADDR" --port "$LISTEN_PORT" --jinja \
+    -dev ROCm0 -ngl 999 -np "$PARALLEL" -c "$CTX_SIZE" \
+    -b "$BATCH_SIZE" -ub "$UBATCH_SIZE" -fa on \
+    -ctk "$CACHE_TYPE_K" -ctv "$CACHE_TYPE_V" -t "$NUM_THREADS" -tb "$THREAD_BATCH" \
+    -ctxcp "$CTX_CHECKPOINTS" --cache-ram "$CACHE_RAM" --cache-prompt --cache-idle-slots --metrics \
+    --kairic-edge --spec-type draft-mtp \
+    --spec-draft-device ROCm0 --spec-draft-ngl 999 \
+    --spec-draft-type-k "$CACHE_TYPE_K" --spec-draft-type-v "$CACHE_TYPE_V" \
+    --spec-draft-n-max "$MTP_N_MAX" --spec-draft-n-min "$MTP_N_MIN" \
+    --spec-draft-p-min "$MTP_P_MIN" --spec-draft-p-split "$MTP_P_SPLIT" \
+    --spec-draft-backend-sampling \
+    --temp "$TEMPERATURE" --top-p "$TOP_P" --top-k "$TOP_K" --min-p "$MIN_P" \
+    --presence-penalty "$PRESENCE_PENALTY" \
+    --reasoning "$REASONING" --reasoning-format "$REASONING_FORMAT" --reasoning-budget -1

tests/frank_large_config.bats

@@ -1,6 +1,6 @@
 #!/usr/bin/env bash
-# Seam: frank-default-large model, runtime, embedded-MTP spec, template.
-# Covers the ROCmI4 embedded-MTP deployment contract (charlie12345/ROCmFPX).
+# Seam: frank-default-large model, runtime, Kairic Edge spec, template.
+# Covers the Kairic Edge deployment contract (ciru-ai/ROCmFPX v1.2).
 #
 # load helpers
 
@@ -11,32 +11,27 @@ SERVE_FILE="$REPO_ROOT/scripts/serve-frank-large.sh"
 UNIT_FILE="$REPO_ROOT/scripts/frank-default-large.service"
 TEMPLATE_FILE="$REPO_ROOT/scripts/chat-template.jinja"
 
-@test "frank-default-large serves the eemin ROCmI4 embedded-MTP GGUF" {
-    grep -q '^MODEL_FILE=Qwen3.8-27B-Q4_0_ROCMI4\.gguf$' "$ENV_FILE"
-    grep -q 'Qwen3.8-27B-Q4_0_ROCMI4\.gguf' "$SERVE_FILE"
-    # The MTP head is embedded in the main GGUF: no separate draft file.
-    grep -q '^MTP_DRAFT_FILE=$' "$ENV_FILE"
-    ! grep -q -- '--model-draft' "$SERVE_FILE"
+@test "frank-default-large serves the Kairic Edge model and sidecars" {
+    grep -q '^MODEL_FILE=Qwen3.8-27B-IU4-Kairic-Edge\.gguf$' "$ENV_FILE"
+    grep -q '^KAIRIC_FFN_SIDECAR=' "$ENV_FILE"
+    grep -q '^KAIRIC_GDN_SIDECAR=' "$ENV_FILE"
+    grep -q '^KAIRIC_GDN_OUTPUT_SIDECAR=' "$ENV_FILE"
+    grep -q -- '--kairic-edge' "$SERVE_FILE"
 }
 
-@test "frank-default-large uses charlie12345 ROCmFPX with ROCmI4 W4A4" {
-    grep -q 'rocmi4-qwen38/ROCmFPX/build-rocmi4-w4a4/bin/llama-server' "$ENV_FILE"
-    grep -q 'eemin-Qwen3.8-27B-ROCMI4-MTP' "$ENV_FILE"
+@test "frank-default-large uses the Kairic Edge ROCmFPX v1.2 runtime" {
+    grep -q 'ROCmFPX/build-kairic/bin/llama-server' "$ENV_FILE"
+    grep -q '^KAIRIC_EDGE_COMPATIBILITY_MODE=1$' "$ENV_FILE"
+    grep -q '205a3e5f40e5542e2f2eb68e3d3f81f918b1d895' "$ENV_FILE"
 }
 
-@test "frank-default-large runs strict-Qwen embedded MTP with backend sampling" {
-    # embedded MTP: draft on ROCm0, all layers, no separate head
+@test "frank-default-large runs Kairic Edge MTP in compatibility mode" {
     grep -q -- '--spec-type draft-mtp' "$SERVE_FILE"
-    grep -q -- '--spec-mtp-strict-qwen' "$SERVE_FILE"
-    grep -q -- '--spec-draft-ngl all' "$SERVE_FILE"
-    grep -q -- '--spec-draft-backend-sampling' "$SERVE_FILE"
+    grep -q -- '--kairic-edge' "$SERVE_FILE"
     grep -qF -- '--spec-draft-n-max "$MTP_N_MAX"' "$SERVE_FILE"
-    grep -qF -- '--spec-draft-p-min "$MTP_P_MIN"' "$SERVE_FILE"
-    # qualified profile tunables are exposed in the env
+    grep -qF -- '--spec-draft-p-split "$MTP_P_SPLIT"' "$SERVE_FILE"
+    grep -q '^KAIRIC_EDGE_COMPATIBILITY_MODE=1$' "$ENV_FILE"
     grep -q '^MTP_N_MAX=4$' "$ENV_FILE"
-    grep -q '^MTP_P_MIN=0.60$' "$ENV_FILE"
-    grep -q '^SPEC_MTP_STRICT_QWEN=on$' "$ENV_FILE"
-    grep -q '^MTP_BACKEND_SAMPLING=on$' "$ENV_FILE"
 }
 
 @test "frank-default-large fits the model and KV cache in unified memory" {
@@ -45,14 +40,14 @@ TEMPLATE_FILE="$REPO_ROOT/scripts/chat-template.jinja"
 }
 
 @test "frank-default-large exposes a swappable ubatch" {
-    grep -q '^UBATCH_SIZE=256$' "$ENV_FILE"
-    grep -q ': "${UBATCH_SIZE:=256}"' "$SERVE_FILE"
+    grep -q '^UBATCH_SIZE=512$' "$ENV_FILE"
+    grep -q ': "${UBATCH_SIZE:=512}"' "$SERVE_FILE"
     grep -q -- '-ub "$UBATCH_SIZE"' "$SERVE_FILE"
 }
 
 @test "frank-default-large uses the tracked Qwen-Sharp template on :7770" {
     grep -q '^CHAT_TEMPLATE_FILE=' "$ENV_FILE"
-    grep -q 'chat-template\.jinja' "$SERVE_FILE"
+    grep -q -- '--jinja' "$SERVE_FILE"
     [ -s "$TEMPLATE_FILE" ]
     grep -q '^ALIAS=frank-default-large$' "$ENV_FILE"
     grep -q '^LISTEN_PORT=7770$' "$ENV_FILE"