Restore historical Q6 large model runtime

scripts/serve-frank-large.sh

@@ -1,6 +1,6 @@
 #!/usr/bin/env bash
 # Serve the kingjones Qwen3.8 Uncensored Q6 AGENT model as frank-default-large.
-# The deployment uses a standalone MTP draft head and Turbo4 V-side KV cache.
+# The deployment uses a standalone MTP draft head and f16 KV cache.
 set -euo pipefail
 
 SCRIPT_DIR="$(cd -- "$(dirname -- "${BASH_SOURCE[0]}")" && pwd)"
@@ -22,13 +22,13 @@ fi
 : "${LISTEN_PORT:=7770}"
 : "${CTX_SIZE:=262144}"
 : "${PARALLEL:=1}"
-: "${BATCH_SIZE:=2048}"
-: "${UBATCH_SIZE:=512}"
+: "${BATCH_SIZE:=4096}"
+: "${UBATCH_SIZE:=4096}"
 : "${NUM_THREADS:=16}"
 : "${THREAD_BATCH:=32}"
 : "${CACHE_TYPE_K:=f16}"
-: "${CACHE_TYPE_V:=turbo4}"
-: "${CTX_CHECKPOINTS:=32}"
+: "${CACHE_TYPE_V:=f16}"
+: "${CTX_CHECKPOINTS:=16}"
 : "${CACHE_RAM:=8192}"
 : "${MTP_N_MAX:=4}"
 : "${MTP_N_MIN:=0}"
@@ -55,14 +55,18 @@ if [[ ! -x "$LLAMA_BIN" ]]; then
     exit 1
 fi
 SERVER_DIR="$(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}"
+ROCM_PATH="${ROCM_DEVEL:-${ROCM_PATH:-/opt/rocm}}"
+if [[ -n "${ROCM_LIB:-}" && -n "${ROCM_CORE:-}" ]]; then
+    LIBRARY_PATH="$ROCM_LIB/lib:$ROCM_CORE/lib:$ROCM_DEVEL/lib/llvm/lib:$SERVER_DIR:${LD_LIBRARY_PATH:-}"
+else
+    LIBRARY_PATH="$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}"
+fi
 
 exec /usr/bin/env \
     ROCM_PATH="$ROCM_PATH" \
     HIP_VISIBLE_DEVICES=0 \
-    HSA_OVERRIDE_GFX_VERSION="$HSA_OVERRIDE_GFX_VERSION" \
     LD_LIBRARY_PATH="$LIBRARY_PATH" \
+    HSA_OVERRIDE_GFX_VERSION="$HSA_OVERRIDE_GFX_VERSION" \
     GGML_CUDA_GRAPH_OPT=0 \
     LLAMA_TARGET_GREEDY_ARGMAX_FASTPATH=0 \
     LLAMA_MTP_CPU_ARGMAX_FASTPATH=1 \