Files
serverAppConfigs/scripts/serve-frank-large.sh
T

121 lines
4.3 KiB
Bash
Executable File

#!/usr/bin/env bash
# Serve jcbtc/Qwen3.8-27B-CIRU-ActiveFPX-PromptForge as frank-default-large
# via the CIRU ROCmFPX llama.cpp runtime on Dankclaw (Strix Halo gfx1151).
#
# Runtime: the PromptForge llama-server built from ciru-ai/ROCmFPX tag
# qwen3.8-activefpx-promptforge-v2.3 (commit 103af8b41) against the private
# TheRock ROCm 7.15 SDK (kept in the retired ling3-ciru venv). The model is
# a GGUF with optional PromptForge companion views (FFN/GDN .pfs) that enable
# CIRU DualView prompt acceleration. Native depth-4 MTP speculative decoding.
#
# The model card requires ROCm 7.15 (not the system ROCm 7.2.4) for the
# advertised Strix Halo performance. LD_LIBRARY_PATH therefore points at the
# 7.15 SDK libraries first. An older system ROCm must not precede them.
#
# Tunables come from frank-default-large.env in this directory unless
# FRANK_LARGE_ENV_FILE overrides that path.
set -euo pipefail
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
# shellcheck disable=SC1090
source "$ENV_FILE"
set +a
fi
# --- defaults (used when the env file does not set them) -------------------
: "${LLAMA_BIN:=/home/dank/ciru-qwen38/ROCmFPX/build-promptforge/bin/llama-server}"
: "${MODEL_DIR:=/home/dank/models/CIRU-Qwen3.8-27B-ActiveFPX}"
: "${MODEL_FILE:=Qwen3.8-27B-CIRU-ActiveFPX-PromptForge-v2.gguf}"
: "${FFN_PFS:=Qwen3.8-27B-CIRU-ActiveFPX-PromptForge-FFN.pfs}"
: "${GDN_PFS:=Qwen3.8-27B-CIRU-ActiveFPX-PromptForge-GDN.pfs}"
: "${ROCM_DEVEL:=/home/dank/ling3-ciru/Ling-3.0-Flash-CIRU-int4-Strix-native/.venv/lib/python3.12/site-packages/_rocm_sdk_devel}"
: "${ROCM_LIB:=/home/dank/ling3-ciru/Ling-3.0-Flash-CIRU-int4-Strix-native/.venv/lib/python3.12/site-packages/_rocm_sdk_libraries}"
: "${ROCM_CORE:=/home/dank/ling3-ciru/Ling-3.0-Flash-CIRU-int4-Strix-native/.venv/lib/python3.12/site-packages/_rocm_sdk_core}"
: "${ALIAS:=frank-default-large}"
: "${BIND_ADDR:=0.0.0.0}"
: "${LISTEN_PORT:=52625}"
: "${CTX_SIZE:=524288}"
: "${PARALLEL:=2}"
: "${BATCH_SIZE:=2048}"
: "${UBATCH_SIZE:=2048}"
: "${CACHE_TYPE_K:=f16}"
: "${CACHE_TYPE_V:=f16}"
: "${CTX_CHECKPOINTS:=16}"
: "${CACHE_RAM:=8192}"
: "${SPEC_DRAFT_N_MAX:=4}"
: "${SPEC_DRAFT_N_MIN:=0}"
: "${SPEC_DRAFT_P_MIN:=0.0}"
: "${SPEC_DRAFT_P_SPLIT:=0.10}"
: "${TEMPERATURE:=0.7}"
: "${TOP_P:=0.95}"
: "${REASONING:=on}"
: "${REASONING_FORMAT:=deepseek}"
: "${VERBOSITY:=4}"
MODEL="$MODEL_DIR/$MODEL_FILE"
export PROMPTFORGE_SIDECAR="$MODEL_DIR/$FFN_PFS"
export PROMPTFORGE_GDN_SIDECAR="$MODEL_DIR/$GDN_PFS"
export PROMPTFORGE_MODE="m2048_fused_tail1476"
export GGML_CUDA_GRAPH_OPT=0
export LLAMA_MTP_CPU_ARGMAX_FASTPATH=1
if [[ ! -f "$MODEL" ]]; then
echo "missing required file: $MODEL" >&2
exit 1
fi
if [[ ! -f "$PROMPTFORGE_SIDECAR" ]]; then
echo "missing PromptForge FFN companion: $PROMPTFORGE_SIDECAR" >&2
exit 1
fi
if [[ ! -f "$PROMPTFORGE_GDN_SIDECAR" ]]; then
echo "missing PromptForge GDN companion: $PROMPTFORGE_GDN_SIDECAR" >&2
exit 1
fi
if [[ ! -x "$LLAMA_BIN" ]]; then
echo "missing llama-server binary: $LLAMA_BIN" >&2
exit 1
fi
# ROCm 7.15 SDK libraries must precede any system ROCm in LD_LIBRARY_PATH.
export ROCM_PATH="$ROCM_DEVEL"
export LD_LIBRARY_PATH="${ROCM_LIB}/lib:${ROCM_CORE}/lib:${ROCM_DEVEL}/lib${LD_LIBRARY_PATH:+:$LD_LIBRARY_PATH}"
exec "$LLAMA_BIN" \
--model "$MODEL" \
--alias "$ALIAS" \
--host "$BIND_ADDR" \
--port "$LISTEN_PORT" \
-dev ROCm0 \
-ngl 999 \
-c "$CTX_SIZE" \
-b "$BATCH_SIZE" \
-ub "$UBATCH_SIZE" \
-fa on \
-ctk "$CACHE_TYPE_K" \
-ctv "$CACHE_TYPE_V" \
-np "$PARALLEL" \
-ctxcp "$CTX_CHECKPOINTS" \
--cache-ram "$CACHE_RAM" \
--cache-prompt \
--metrics \
--no-mmap \
--spec-type draft-mtp \
--spec-draft-device ROCm0 \
--spec-draft-ngl 999 \
--spec-draft-type-k f16 \
--spec-draft-type-v f16 \
--spec-draft-n-max "$SPEC_DRAFT_N_MAX" \
--spec-draft-n-min "$SPEC_DRAFT_N_MIN" \
--spec-draft-p-min "$SPEC_DRAFT_P_MIN" \
--spec-draft-p-split "$SPEC_DRAFT_P_SPLIT" \
--spec-draft-backend-sampling \
--temp "$TEMPERATURE" \
--top-p "$TOP_P" \
--reasoning "$REASONING" \
--reasoning-format "$REASONING_FORMAT" \
--reasoning-budget -1 \
-lv "$VERBOSITY"