Frank
55f87fcdce
The 2026-10-09 wire aliases become the service names everywhere: systemd units, serve scripts, env files and FRANK_* variables, deploy-plan/deploy-remote service keys, container names, Prometheus job names + alert rules, Grafana dashboard queries, bats seams, runbook filenames, homepage/AGENTS lore, and historical prose. Rollback tags renamed in lockstep. Residue in the tree: zero. Retired frank-medium/small/npu names are history and stay. Known casualty: scripts/patches/*.patch context lines were rewritten; those retired-era vLLM-fork patches no longer apply byte-exact.
90 lines
3.9 KiB
Bash
Executable File
90 lines
3.9 KiB
Bash
Executable File
#!/usr/bin/env bash
|
|
# Build the ROCmFPX runtime that serves frank-dragoon on Dankclaw.
|
|
#
|
|
# bash scripts/build-rocmfpx.sh # clone/fetch + build the pin
|
|
# bash scripts/build-rocmfpx.sh --verify # only check the installed tree
|
|
#
|
|
# Runtime: kingjones30/ROCmFPX — charlie12345/ROCmFPX plus the model-card
|
|
# patches, i.e. the fork that owns the ROCmFPx tensor formats. frank-dragoon's
|
|
# payload is ftype 115 (`Q8_0_ROCMFPX_AGENT`): 311 tensors of
|
|
# GGML_TYPE_Q8_0_ROCMFPX (103), a type that exists ONLY in this fork, so
|
|
# stock llama.cpp, gufo and every other loader on the host reject the file.
|
|
# This is the same tree that served the Qwen3.8-Flash-Next ROCmFP4 STRIX
|
|
# endpoint 2026-08-30 → 09-11 (see the kingjones runbook), rebuilt here so a
|
|
# fresh host can be brought up from the repo alone.
|
|
#
|
|
# Why this commit and not a newer one: 36e9acd (2026-08-28) is what was
|
|
# qualified against this payload on 2026-10-02 — it loads ftype 115, survives
|
|
# warmup, and drafts with the MTP head at acceptance 0.65. The five legacy
|
|
# builds of 2026-08-25 crashed this same file in ggml_compute_forward_set_rows
|
|
# (see kingjones-q8agent-rocmfpx.md), so the pin is load-bearing: do not bump
|
|
# it without re-running that crash test.
|
|
#
|
|
# Host notes:
|
|
# * -DLLAMA_BUILD_WEBUI=OFF is REQUIRED on this box. The tree provisions its
|
|
# embedded UI assets via npm or the HF llama-ui bucket; npm is absent here
|
|
# and the bucket download half-failed, aborting the link at 98%. The API
|
|
# server is unaffected.
|
|
# * The build links against the host ROCm (/opt/rocm); no bundled toolchain
|
|
# like the gfx1201 R9700 build needed.
|
|
set -euo pipefail
|
|
|
|
ROCMFPX_REPO="${ROCMFPX_REPO:-https://github.com/kingjones30/ROCmFPX.git}"
|
|
# The commit frank-dragoon was qualified with (measured 2026-10-02).
|
|
ROCMFPX_COMMIT="${ROCMFPX_COMMIT:-36e9acd40e10a87cd3c3ef8ec734668757dc8520}"
|
|
SRC_DIR="${ROCMFPX_SRC_DIR:-/home/dank/GitPackages/kingjones-ROCmFPX}"
|
|
BUILD_DIR="${ROCMFPX_BUILD_DIR:-$SRC_DIR/build}"
|
|
GPU_TARGET="${ROCMFPX_GPU_TARGET:-gfx1151}"
|
|
JOBS="${JOBS:-$(nproc)}"
|
|
|
|
# check_pin — refuse a source tree that is not the qualified commit. A moved
|
|
# fork means different kernels under the same path, and on this model line a
|
|
# wrong build is a segfault at first request, not a clean error.
|
|
check_pin() {
|
|
local commit
|
|
commit="$(git -C "$SRC_DIR" rev-parse HEAD 2>/dev/null || true)"
|
|
if [[ -n "$commit" && "$commit" != "$ROCMFPX_COMMIT" ]]; then
|
|
echo "ROCMFPX_COMMIT mismatch: $SRC_DIR is at $commit, pinned $ROCMFPX_COMMIT" >&2
|
|
exit 1
|
|
fi
|
|
}
|
|
|
|
if [[ "${1:-}" == "--verify" ]]; then
|
|
check_pin
|
|
[[ -x "$BUILD_DIR/bin/llama-server" ]] || {
|
|
echo "no ROCmFPX llama-server at $BUILD_DIR/bin/llama-server" >&2
|
|
exit 1
|
|
}
|
|
# The format the endpoint exists for: the fork must carry the ROCmFPx
|
|
# tensor type, or the payload cannot load at all.
|
|
"$BUILD_DIR/bin/llama-server" --help 2>&1 | grep -q -- '--spec-type' || {
|
|
echo "$BUILD_DIR/bin/llama-server has no --spec-type: MTP drafting is impossible" >&2
|
|
exit 1
|
|
}
|
|
"$BUILD_DIR/bin/llama-server" --version | head -1
|
|
exit 0
|
|
fi
|
|
|
|
echo "== source: $ROCMFPX_REPO @ $ROCMFPX_COMMIT =="
|
|
if [[ ! -d "$SRC_DIR/.git" ]]; then
|
|
mkdir -p "$(dirname "$SRC_DIR")"
|
|
git clone "$ROCMFPX_REPO" "$SRC_DIR"
|
|
fi
|
|
git -C "$SRC_DIR" fetch --quiet origin "$ROCMFPX_COMMIT" || true
|
|
git -C "$SRC_DIR" checkout -q --detach "$ROCMFPX_COMMIT"
|
|
check_pin
|
|
echo " $(git -C "$SRC_DIR" rev-parse HEAD)"
|
|
|
|
echo "== configure + build (release, HIP $GPU_TARGET) =="
|
|
cmake -S "$SRC_DIR" -B "$BUILD_DIR" \
|
|
-DGGML_HIP=ON \
|
|
-DGPU_TARGETS="$GPU_TARGET" \
|
|
-DGGML_NATIVE=ON \
|
|
-DCMAKE_BUILD_TYPE=Release \
|
|
-DLLAMA_BUILD_WEBUI=OFF
|
|
cmake --build "$BUILD_DIR" --target llama-server llama-quantize -j "$JOBS"
|
|
|
|
echo "== verify =="
|
|
"$BUILD_DIR/bin/llama-server" --version | head -1
|
|
echo "frank-dragoon runtime ready: $BUILD_DIR/bin/llama-server ($ROCMFPX_COMMIT)"
|