frank-large: swap to Kairic Edge 27B IU4 (W4A4) on Strix Halo
Replace the unsloth llama.cpp prebuilt (b11030, Qwen3.8-Flash-Next UD-IQ4_XS, 125B MoE) with the Kairic Edge runtime (ciru-ai/ROCmFPX, branch kairic-edge-qwen38-27b-v1.2, commit 205a3e5) serving jcbtc/Qwen3.8-27B-IU4-Kairic-Edge (27B dense, IU4 W4A4). - Runtime: built from source (scripts/build-kairic-edge-gfx1151.sh), TheRock 7.15.0a20260718 toolchain, CK fdf4bb7f + gfx1151-iu4 patch. - Shape: one stream, full 262144 context (the model's native window), 1 slot, 8 GiB prompt-cache budget. - Spec method: native MTP depth 4 + n-gram drafting (24/64/64). DFlash is NOT available for this model (no DRAFT_DFLASH spec type). - Compatibility mode: the harness needs sampling, tools and a reasoning budget, which fast-greedy rejects. COMPATIBILITY_MODE=1 enables them. - Reasoning: enabled (auto + deepseek format, thoughts land in reasoning_content). - Payload: 4 files (15.5 GiB GGUF + 7.99 GiB FFN + 1.88 GiB GDN + 0.70 GiB GDN-Output), sha256-verified (scripts/download-frank-large-kairic.sh).
This commit is contained in:
Frank
Executable
+96
@@ -0,0 +1,96 @@
|
||||
#!/usr/bin/env bash
|
||||
set -euo pipefail
|
||||
|
||||
readonly repo_root="$(cd -- "$(dirname -- "${BASH_SOURCE[0]}")/.." && pwd)"
|
||||
readonly ck_root="${KAIRIC_CK_ROOT:-$repo_root/third_party/composable_kernel}"
|
||||
readonly ck_commit=fdf4bb7fcc984811cef48ce817d89aac064b984a
|
||||
readonly ck_patch="$repo_root/patches/composable-kernel-gfx1151-iu4.patch"
|
||||
readonly build_dir="${BUILD_DIR:-$repo_root/build-kairic}"
|
||||
readonly rocm="${ROCM_PATH:-/opt/rocm}"
|
||||
readonly jobs="${JOBS:-$(nproc)}"
|
||||
|
||||
for tool in cmake git ninja; do
|
||||
command -v "$tool" >/dev/null || {
|
||||
echo "missing required tool: $tool" >&2
|
||||
exit 1
|
||||
}
|
||||
done
|
||||
|
||||
[[ -f "$ck_patch" ]] || {
|
||||
echo "missing Composable Kernel patch: $ck_patch" >&2
|
||||
exit 1
|
||||
}
|
||||
|
||||
if [[ ! -d "$ck_root/.git" ]]; then
|
||||
mkdir -p "$(dirname -- "$ck_root")"
|
||||
git clone https://github.com/ROCm/composable_kernel.git "$ck_root"
|
||||
fi
|
||||
|
||||
git -C "$ck_root" checkout "$ck_commit"
|
||||
if git -C "$ck_root" diff --quiet; then
|
||||
git -C "$ck_root" apply --check "$ck_patch"
|
||||
git -C "$ck_root" apply "$ck_patch"
|
||||
elif git -C "$ck_root" apply --reverse --check "$ck_patch"; then
|
||||
echo "Composable Kernel release patch is already applied"
|
||||
else
|
||||
echo "Composable Kernel checkout does not match the pinned patch" >&2
|
||||
exit 1
|
||||
fi
|
||||
|
||||
if [[ -x "$rocm/bin/amdclang++" ]]; then
|
||||
hip_compiler="$rocm/bin/amdclang++"
|
||||
elif [[ -x "$rocm/llvm/bin/clang++" ]]; then
|
||||
hip_compiler="$rocm/llvm/bin/clang++"
|
||||
else
|
||||
echo "cannot find a HIP compiler below ROCM_PATH=$rocm" >&2
|
||||
exit 1
|
||||
fi
|
||||
|
||||
if [[ -n "${CC:-}" ]]; then
|
||||
c_compiler="$(command -v "$CC")"
|
||||
elif [[ -x /usr/bin/gcc ]]; then
|
||||
c_compiler=/usr/bin/gcc
|
||||
else
|
||||
c_compiler="$(command -v gcc)"
|
||||
fi
|
||||
if [[ -n "${CXX:-}" ]]; then
|
||||
cxx_compiler="$(command -v "$CXX")"
|
||||
elif [[ -x /usr/bin/g++ ]]; then
|
||||
cxx_compiler=/usr/bin/g++
|
||||
else
|
||||
cxx_compiler="$(command -v g++)"
|
||||
fi
|
||||
|
||||
export ROCM_PATH="$rocm"
|
||||
export PATH="$rocm/bin:$rocm/lib/llvm/bin:$rocm/llvm/bin:$PATH"
|
||||
export LD_LIBRARY_PATH="$rocm/lib:$rocm/lib/rocm_sysdeps/lib:$rocm/lib/llvm/lib:$rocm/llvm/lib${LD_LIBRARY_PATH:+:$LD_LIBRARY_PATH}"
|
||||
readonly hip_flags="-DGGML_ROCMFPX_RDNA35_MMID_MAX_BATCH=5 -DGGML_ROCMFPX_MOE_MMVQ_ROWS_PER_BLOCK=4${KAIRIC_HIP_TOOLCHAIN_FLAGS:+ $KAIRIC_HIP_TOOLCHAIN_FLAGS}"
|
||||
|
||||
cmake -S "$repo_root" -B "$build_dir" -G Ninja \
|
||||
-DCMAKE_BUILD_TYPE=Release \
|
||||
-DCMAKE_C_COMPILER="$c_compiler" \
|
||||
-DCMAKE_CXX_COMPILER="$cxx_compiler" \
|
||||
-DCMAKE_HIP_COMPILER="$hip_compiler" \
|
||||
-DCMAKE_HIP_FLAGS="$hip_flags" \
|
||||
-DCMAKE_PREFIX_PATH="$rocm" \
|
||||
-DBUILD_SHARED_LIBS=ON \
|
||||
-DGGML_CPU=ON -DGGML_OPENMP=ON -DGGML_HIP=ON -DGGML_CUDA=OFF \
|
||||
-DGGML_VULKAN=OFF -DGGML_HIP_FORCE_MMQ=ON -DGGML_HIP_GRAPHS=ON \
|
||||
-DGGML_HIP_MMQ_MFMA=ON -DGGML_HIP_NO_VMM=ON \
|
||||
-DGGML_HIP_ROCWMMA_FATTN=OFF -DGGML_NATIVE=ON \
|
||||
-DAMDGPU_TARGETS=gfx1151 -DGPU_BUILD_TARGETS=gfx1151 \
|
||||
-DPROMPTFORGE_CK_ROOT="$ck_root" \
|
||||
-DLLAMA_BUILD_WEBUI=OFF \
|
||||
-DGGML_BUILD_TESTS=OFF -DLLAMA_BUILD_TESTS=OFF -DLLAMA_BUILD_SERVER=ON
|
||||
|
||||
cmake --build "$build_dir" --target llama-server -j"$jobs"
|
||||
|
||||
"$build_dir/bin/llama-server" --version
|
||||
"$build_dir/bin/llama-server" --help | grep -A1 -- '--kairic-edge'
|
||||
ldd "$build_dir/bin/llama-server" 2>&1 | tee "$build_dir/llama-server.ldd.txt"
|
||||
if grep -Eiq 'not found|version .* required by .* not found' "$build_dir/llama-server.ldd.txt"; then
|
||||
echo "runtime dependency verification failed" >&2
|
||||
exit 1
|
||||
fi
|
||||
|
||||
echo "Kairic Edge runtime built at $build_dir/bin/llama-server"
|
||||
+13
-12
@@ -1072,20 +1072,21 @@ deploy_anubis() {
|
||||
wait_container_healthy anubis 60 || return 1
|
||||
}
|
||||
|
||||
# frank-large is the unsloth llama.cpp prebuilt (b11030-mix-5ff778e, ROCm
|
||||
# gfx1151) serving unsloth/Qwen3.8-Flash-Next-GGUF:UD-IQ4_XS on the Strix
|
||||
# Halo iGPU, as a ROOT unit since the 2026-09-19 cutover: the runtime is a
|
||||
# prebuilt tarball with its own bundled ROCm, so there is no container
|
||||
# image to install and no generated unit to dodge. relink_unit points
|
||||
# frank-large is the Kairic Edge runtime (ciru-ai/ROCmFPX, branch
|
||||
# kairic-edge-qwen38-27b-v1.2, commit 205a3e5) serving
|
||||
# jcbtc/Qwen3.8-27B-IU4-Kairic-Edge on the Strix Halo iGPU, as a ROOT
|
||||
# unit since the 2026-09-19 cutover: the runtime is built from source
|
||||
# (scripts/build-kairic-edge-gfx1151.sh), so there is no container image
|
||||
# to install and no generated unit to dodge. relink_unit points
|
||||
# /etc/systemd/system/frank-large.service at the repo file and boot
|
||||
# persistence is that unit's [Install] section.
|
||||
#
|
||||
# It replaces the CIRU v4.4.1 Orca runtime (jcbtc/Qwen3.8-Flash-CIRU-
|
||||
# STRIX-Orca), which had replaced the halogen-flash-server quadlet. The
|
||||
# port gate is the same as every cutover since 2026-09-16: nothing starts
|
||||
# It replaces the unsloth llama.cpp prebuilt (b11030-mix-5ff778e, ROCm
|
||||
# gfx1151), which had replaced the CIRU v4.4.1 Orca runtime. The port
|
||||
# gate is the same as every cutover since 2026-09-16: nothing starts
|
||||
# until 7770 is released.
|
||||
LLM_LARGE_MODEL="${LLM_LARGE_MODEL:-/home/dank/models/Qwen3.8-Flash-Next-UD-IQ4_XS/UD-IQ4_XS/Qwen3.8-Flash-Next-UD-IQ4_XS-00001-of-00003.gguf}"
|
||||
LLM_LARGE_DRAFT="${LLM_LARGE_DRAFT:-/home/dank/models/Qwen3.8-Flash-Next-UD-IQ4_XS/mtp/mtp-Qwen3.8-Flash-Next-shared-Q8_0.gguf}"
|
||||
LLM_LARGE_MODEL="${LLM_LARGE_MODEL:-/home/dank/models/Qwen3.8-27B-IU4-Kairic-Edge/Qwen3.8-27B-IU4-Kairic-Edge.gguf}"
|
||||
LLM_LARGE_DRAFT="${LLM_LARGE_DRAFT:-/home/dank/models/Qwen3.8-27B-IU4-Kairic-Edge/Qwen3.8-27B-Kairic-IU4-FFN.pfs}"
|
||||
|
||||
retire_halogen_large_quadlet() {
|
||||
local trash="$HOME/.AGENTTRASH/20260919-orca-cutover/quadlet"
|
||||
@@ -1125,7 +1126,7 @@ deploy_llm_large() {
|
||||
for f in "$LLM_LARGE_MODEL" "$LLM_LARGE_DRAFT"; do
|
||||
if [[ ! -f "$f" ]]; then
|
||||
echo "ERROR: payload absent at $f" >&2
|
||||
echo "frank-large: fetch it: bash scripts/download-frank-large-unsloth.sh" >&2
|
||||
echo "frank-large: fetch it: bash scripts/download-frank-large-kairic.sh" >&2
|
||||
missing=1
|
||||
fi
|
||||
done
|
||||
@@ -1140,7 +1141,7 @@ deploy_llm_large() {
|
||||
# The pattern never appears in the deploying shell's own command line, so
|
||||
# -f is safe here (it is not in `bash deploy-remote.sh`).
|
||||
run_privileged systemctl stop frank-large.service 2>/dev/null || true
|
||||
pkill -f 'Qwen3.8-Flash-Next-UD-IQ4_XS' 2>/dev/null || true
|
||||
pkill -f 'Qwen3.8-27B-IU4-Kairic-Edge' 2>/dev/null || true
|
||||
# Nothing may start until the predecessor has released the port. On
|
||||
# 2026-09-16 the cutover failed exactly here: the old server logged
|
||||
# "Deactivated successfully", the next engine tried to bind 7770 a second
|
||||
|
||||
Executable
+110
@@ -0,0 +1,110 @@
|
||||
#!/usr/bin/env bash
|
||||
# Download jcbtc/Qwen3.8-27B-IU4-Kairic-Edge (the frank-large model) on
|
||||
# Dankclaw.
|
||||
#
|
||||
# bash scripts/download-frank-large-kairic.sh
|
||||
# bash scripts/download-frank-large-kairic.sh --verify-only
|
||||
#
|
||||
# The Kairic Edge payload is four files: the main IU4 GGUF (15.5 GiB) and
|
||||
# three .pfs sidecars (FFN 7.99 GiB, GDN 1.88 GiB, GDN-Output 0.70 GiB).
|
||||
# The sidecars are the PromptForge IU4 (W4A4) weight shards the Kairic Edge
|
||||
# runtime loads alongside the main GGUF (PROMPTFORGE_IU4_SIDECAR,
|
||||
# PROMPTFORGE_GDN_SIDECAR, PROMPTFORGE_GDN_OUTPUT_SIDECAR).
|
||||
#
|
||||
# Integrity: every file is checked against its declared byte count and sha256
|
||||
# (the values below are the LFS oids from the Hub, 2026-09-21). The repo is
|
||||
# public (gated: false); an HF token at ~/.cache/huggingface/token is used
|
||||
# when present to clear the anonymous rate limit on a 26 GB transfer.
|
||||
#
|
||||
# Layout after a successful run (MODEL_DIR):
|
||||
# Qwen3.8-27B-IU4-Kairic-Edge.gguf 16617792672 main IU4 GGUF
|
||||
# Qwen3.8-27B-Kairic-IU4-FFN.pfs 8576856064 FFN sidecar
|
||||
# Qwen3.8-27B-Kairic-IU4-GDN.pfs 2019569664 GDN sidecar
|
||||
# Qwen3.8-27B-Kairic-IU4-GDN-Output.pfs 756953088 GDN-Output sidecar
|
||||
set -euo pipefail
|
||||
|
||||
REPO="jcbtc/Qwen3.8-27B-IU4-Kairic-Edge"
|
||||
MODEL_DIR="/home/dank/models/Qwen3.8-27B-IU4-Kairic-Edge"
|
||||
BASE="https://huggingface.co/$REPO/resolve/main"
|
||||
|
||||
mode="download"
|
||||
[[ "${1:-}" == "--verify-only" ]] && mode="verify"
|
||||
|
||||
token=""
|
||||
auth=()
|
||||
if [[ -r "$HOME/.cache/huggingface/token" ]]; then
|
||||
token="$(tr -d '[:space:]' < "$HOME/.cache/huggingface/token")"
|
||||
auth=(-H "Authorization: Bearer $token")
|
||||
fi
|
||||
|
||||
dl() { # dl <relpath>
|
||||
local rel="$1" dest="$MODEL_DIR/$rel"
|
||||
[[ -s "$dest" ]] && return 0
|
||||
mkdir -p "$(dirname "$dest")"
|
||||
echo "fetching $rel"
|
||||
curl -fL -C - "${auth[@]}" --retry 5 --retry-delay 3 -o "$dest" "$BASE/$rel"
|
||||
}
|
||||
|
||||
# filename size sha256 — the LFS oids from the Hub (2026-09-21)
|
||||
FILES=(
|
||||
"Qwen3.8-27B-IU4-Kairic-Edge.gguf 16617792672 360caf7381907c3eca7ac0afd1228efc016af747f3f38637fb1c7f94daabac2a"
|
||||
"Qwen3.8-27B-Kairic-IU4-FFN.pfs 8576856064 adcbb90a7b429a30a2a39043366d68320d72e8b4816a0f498e882b2f80a2ba2b"
|
||||
"Qwen3.8-27B-Kairic-IU4-GDN.pfs 2019569664 82f931316f1c895da104915dec4697163808d06f0e6b2dc027cee7aa3afc0f0e"
|
||||
"Qwen3.8-27B-Kairic-IU4-GDN-Output.pfs 756953088 3b07e7b176559e4402924ba0c368532fa6f02118a33c71e70974c809bf6208a3"
|
||||
)
|
||||
|
||||
RELS=()
|
||||
for line in "${FILES[@]}"; do
|
||||
read -r rel _ _ <<<"$line"
|
||||
RELS+=("$rel")
|
||||
done
|
||||
|
||||
# Verify each file's byte count and sha256 (idempotent: a complete file is
|
||||
# re-checked, not re-downloaded).
|
||||
echo "verifying $MODEL_DIR against declared sizes + sha256"
|
||||
python3 - "$MODEL_DIR" "${RELS[@]}" <<'PY'
|
||||
import hashlib, os, sys
|
||||
model_dir = sys.argv[1]
|
||||
rels = sys.argv[2:]
|
||||
# (rel, size, sha256) triples, re-parsed from the same source of truth.
|
||||
specs = {
|
||||
"Qwen3.8-27B-IU4-Kairic-Edge.gguf": (16617792672, "360caf7381907c3eca7ac0afd1228efc016af747f3f38637fb1c7f94daabac2a"),
|
||||
"Qwen3.8-27B-Kairic-IU4-FFN.pfs": (8576856064, "adcbb90a7b429a30a2a39043366d68320d72e8b4816a0f498e882b2f80a2ba2b"),
|
||||
"Qwen3.8-27B-Kairic-IU4-GDN.pfs": (2019569664, "82f931316f1c895da104915dec4697163808d06f0e6b2dc027cee7aa3afc0f0e"),
|
||||
"Qwen3.8-27B-Kairic-IU4-GDN-Output.pfs": (756953088, "3b07e7b176559e4402924ba0c368532fa6f02118a33c71e70974c809bf6208a3"),
|
||||
}
|
||||
ok = True
|
||||
for rel in rels:
|
||||
dest = os.path.join(model_dir, rel)
|
||||
size, sha = specs[rel]
|
||||
if not os.path.isfile(dest):
|
||||
print(f" MISSING {rel}")
|
||||
ok = False
|
||||
continue
|
||||
actual_size = os.path.getsize(dest)
|
||||
if actual_size != size:
|
||||
print(f" SIZE MISMATCH {rel}: {actual_size} != {size}")
|
||||
ok = False
|
||||
continue
|
||||
h = hashlib.sha256()
|
||||
with open(dest, "rb") as f:
|
||||
for chunk in iter(lambda: f.read(1 << 24), b""):
|
||||
h.update(chunk)
|
||||
actual_sha = h.hexdigest()
|
||||
if actual_sha != sha:
|
||||
print(f" SHA256 MISMATCH {rel}: {actual_sha}")
|
||||
ok = False
|
||||
continue
|
||||
print(f" OK {rel} ({actual_size} bytes)")
|
||||
if not ok:
|
||||
sys.exit(1)
|
||||
PY
|
||||
|
||||
if [[ "$mode" == "download" ]]; then
|
||||
for line in "${FILES[@]}"; do
|
||||
read -r rel _ _ <<<"$line"
|
||||
dl "$rel"
|
||||
done
|
||||
fi
|
||||
|
||||
echo "frank-large payload complete: $MODEL_DIR"
|
||||
+25
-22
@@ -1,6 +1,6 @@
|
||||
# frank-large — unsloth llama.cpp prebuilt (b11030-mix-5ff778e, ROCm
|
||||
# gfx1151) serving unsloth/Qwen3.8-Flash-Next-GGUF:UD-IQ4_XS on the Strix
|
||||
# Halo iGPU.
|
||||
# frank-large — Kairic Edge runtime (ciru-ai/ROCmFPX, branch
|
||||
# kairic-edge-qwen38-27b-v1.2, commit 205a3e5) serving
|
||||
# jcbtc/Qwen3.8-27B-IU4-Kairic-Edge on the Strix Halo iGPU (gfx1151).
|
||||
#
|
||||
# These are the tunables read by scripts/serve-frank-large.sh. The flag
|
||||
# list is owned by the serve script; this file only sets fleet values.
|
||||
@@ -9,31 +9,34 @@
|
||||
# runtime reads those bare (the 2026-08-13 TEMP incident). HOST is the one
|
||||
# exception because the serve script itself consumes it for --host.
|
||||
|
||||
# The assembled payload (scripts/download-frank-large-unsloth.sh): the
|
||||
# serve script refuses to start without the main GGUF and the MTP head.
|
||||
MODEL_DIR=/home/dank/models/Qwen3.8-Flash-Next-UD-IQ4_XS
|
||||
# The assembled payload (scripts/download-frank-large-kairic.sh): the
|
||||
# serve script refuses to start without the main GGUF and the three
|
||||
# sidecars (FFN, GDN, GDN-Output).
|
||||
MODEL_DIR=/home/dank/models/Qwen3.8-27B-IU4-Kairic-Edge
|
||||
|
||||
# The prebuilt runtime (see the serve script for the fetch line).
|
||||
RUNTIME_DIR=/home/dank/GitPackages/unsloth-llama-b11030
|
||||
# The Kairic Edge runtime (scripts/build-kairic-edge-gfx1151.sh).
|
||||
RUNTIME_DIR=/home/dank/GitPackages/ROCmFPX-kairic/build-kairic
|
||||
|
||||
# Fleet endpoint: the same port and alias the CIRU predecessor served, so
|
||||
# Fleet endpoint: the same port and alias the unsloth predecessor served, so
|
||||
# no client, probe or models.yml entry changes address.
|
||||
HOST=0.0.0.0
|
||||
PORT=7770
|
||||
|
||||
# One stream, 200k context (operator's call, 2026-09-21). The model's
|
||||
# trained window is 262144; 200000 is the requested serving shape.
|
||||
CONTEXT_SIZE=200000
|
||||
# One stream, full 262144 context (the model's native window).
|
||||
CONTEXT_SIZE=262144
|
||||
PARALLEL_SLOTS=1
|
||||
|
||||
# MTP shared-Q8_0 head: on. Draft depth 2 is the model card's default
|
||||
# ("higher drafts more but each guess is accepted less often"). The shared
|
||||
# head borrows the token embedding and output projection from the main
|
||||
# model, so the file is 2.6 GB rather than 4.1.
|
||||
ENABLE_MTP=1
|
||||
SPEC_DRAFT_N_MAX=2
|
||||
# Native MTP depth 4 (the model's MTP layers) + n-gram drafting (24/64/64).
|
||||
# DFlash is NOT available for this model (no DRAFT_DFLASH spec type in the
|
||||
# Kairic Edge runtime).
|
||||
SPEC_DRAFT_N_MAX=4
|
||||
|
||||
# Text-only for now: the F16 projector is on disk at vision/mmproj-F16.gguf;
|
||||
# flip to 1 to enable it. The fleet's image path is frank-small either way,
|
||||
# so models.yml stays input: [text] until this changes.
|
||||
ENABLE_VISION=0
|
||||
# The harness needs sampling, tools and a reasoning budget, which the
|
||||
# fast-greedy path rejects. COMPATIBILITY_MODE=1 enables them (9.7% slower
|
||||
# per the build guide).
|
||||
COMPATIBILITY_MODE=1
|
||||
|
||||
# Prompt-cache budget: 8 GiB (the Kairic Edge qualified config). The model
|
||||
# is 27B dense (not DeltaNet), so the fleet's 12.8 GiB DeltaNet floor does
|
||||
# not apply.
|
||||
CACHE_RAM=8192
|
||||
|
||||
@@ -1,5 +1,5 @@
|
||||
[Unit]
|
||||
Description=unsloth llama.cpp (b11030, ROCm gfx1151) Qwen3.8-Flash-Next UD-IQ4_XS (dankclaw, frank-large, Strix Halo iGPU)
|
||||
Description=Kairic Edge (ROCmFPX v1.2, gfx1151) Qwen3.8-27B IU4 W4A4 (dankclaw, frank-large, Strix Halo iGPU)
|
||||
After=network-online.target
|
||||
Wants=network-online.target
|
||||
|
||||
|
||||
+102
-79
@@ -1,21 +1,34 @@
|
||||
#!/usr/bin/env bash
|
||||
# Serve unsloth/Qwen3.8-Flash-Next-GGUF:UD-IQ4_XS as frank-large on
|
||||
# Dankclaw's Strix Halo iGPU (gfx1151), using the unsloth llama.cpp
|
||||
# prebuilt (b11030-mix-5ff778e, ROCm gfx1151) — the first runtime with an
|
||||
# MTP graph for the qwen4exp architecture (stock ggml-org mainline has no
|
||||
# MTP graph, no cross-model tensor borrowing and no --spec-type draft-mtp
|
||||
# for this model).
|
||||
# Serve jcbtc/Qwen3.8-27B-IU4-Kairic-Edge as frank-large on
|
||||
# Dankclaw's Strix Halo iGPU (gfx1151), using the Kairic Edge runtime
|
||||
# (ciru-ai/ROCmFPX, branch kairic-edge-qwen38-27b-v1.2, commit 205a3e5) —
|
||||
# the qualified IU4 (W4A4) serving path with the FFN, GDN and GDN-Output
|
||||
# sidecars.
|
||||
#
|
||||
# Runtime: the prebuilt app tarball from the unslothai/llama.cpp releases
|
||||
# (tag b11030-mix-5ff778e or newer), extracted under
|
||||
# /home/dank/GitPackages/unsloth-llama-b11030/. It bundles its own ROCm
|
||||
# runtime, so there is no host SDK to gate on and no venv to symlink.
|
||||
# Runtime: built from source (scripts/build-kairic-edge-gfx1151.sh), output at
|
||||
# /home/dank/GitPackages/ROCmFPX-kairic/build-kairic/bin/llama-server. The
|
||||
# Kairic Edge path is a llama.cpp build with the PromptForge sidecar env
|
||||
# block (the certified runner's exact env + flags).
|
||||
#
|
||||
# Shape: one stream, 200k context (operator's call, 2026-09-21), all layers
|
||||
# on the iGPU (-ngl 999). The 87 GiB model lives in the iGPU's GTT aperture
|
||||
# over the shared LPDDR (gtt_total ~114 GiB), the same regime the CIRU
|
||||
# Orca predecessor ran in. The MTP shared-Q8_0 head speculates (1.3-1.7x at
|
||||
# concurrency 1, per the model card).
|
||||
# Shape: one stream, full 262144 context (the model's native window), all
|
||||
# layers on the iGPU (-ngl 999). The 27B dense model (15.5 GiB GGUF + 7.99
|
||||
# GiB FFN sidecar + 1.88 GiB GDN sidecar + 0.70 GiB GDN-Output sidecar)
|
||||
# fits the iGPU's GTT aperture (~114 GiB).
|
||||
#
|
||||
# Spec method: native MTP depth 4 (the model's MTP layers) + n-gram drafting
|
||||
# (24/64/64). DFlash is NOT available for this model (no DRAFT_DFLASH spec
|
||||
# type in the Kairic Edge runtime).
|
||||
#
|
||||
# Compatibility mode: the harness needs sampling, tools and a reasoning
|
||||
# budget, which the fast-greedy path rejects. COMPATIBILITY_MODE=1 enables
|
||||
# them (9.7% slower per the build guide). Reasoning is enabled (auto +
|
||||
# deepseek format, so thoughts land in reasoning_content).
|
||||
#
|
||||
# The Qwen3.8 family template keeps prior thinking blocks across turns when
|
||||
# preserve_thinking is set; pass --jinja and the kwarg so multi-turn agents
|
||||
# do not lose the trail. A request-level chat_template_kwargs still wins.
|
||||
# The template gates reasoning_effort to {xhigh, medium, low} — the harness
|
||||
# folds its levels onto that set in models.yml (reasoningEffortMap).
|
||||
#
|
||||
# Tunables come from frank-large.env unless FRANK_LARGE_ENV_FILE overrides
|
||||
# it; anything not set there falls through to the defaults below.
|
||||
@@ -24,85 +37,95 @@ set -euo pipefail
|
||||
SCRIPT_DIR="$(cd -- "$(dirname -- "${BASH_SOURCE[0]}")" && pwd)"
|
||||
ENV_FILE="${FRANK_LARGE_ENV_FILE:-$SCRIPT_DIR/frank-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) ------------------
|
||||
: "${RUNTIME_DIR:=/home/dank/GitPackages/unsloth-llama-b11030}"
|
||||
: "${MODEL_DIR:=/home/dank/models/Qwen3.8-Flash-Next-UD-IQ4_XS}"
|
||||
: "${RUNTIME_DIR:=/home/dank/GitPackages/ROCmFPX-kairic/build-kairic}"
|
||||
: "${MODEL_DIR:=/home/dank/models/Qwen3.8-27B-IU4-Kairic-Edge}"
|
||||
: "${HOST:=0.0.0.0}"
|
||||
: "${PORT:=7770}"
|
||||
: "${CONTEXT_SIZE:=200000}"
|
||||
: "${CONTEXT_SIZE:=262144}"
|
||||
: "${PARALLEL_SLOTS:=1}"
|
||||
: "${ENABLE_MTP:=1}"
|
||||
: "${SPEC_DRAFT_N_MAX:=2}"
|
||||
: "${ENABLE_VISION:=0}"
|
||||
: "${SPEC_DRAFT_N_MAX:=4}"
|
||||
: "${COMPATIBILITY_MODE:=1}"
|
||||
: "${CACHE_RAM:=8192}"
|
||||
|
||||
SERVER_BIN="$RUNTIME_DIR/llama-server"
|
||||
SERVER_BIN="$RUNTIME_DIR/bin/llama-server"
|
||||
MODEL_FILE="$MODEL_DIR/Qwen3.8-27B-IU4-Kairic-Edge.gguf"
|
||||
FFN_SIDECAR="$MODEL_DIR/Qwen3.8-27B-Kairic-IU4-FFN.pfs"
|
||||
GDN_SIDECAR="$MODEL_DIR/Qwen3.8-27B-Kairic-IU4-GDN.pfs"
|
||||
GDN_OUTPUT_SIDECAR="$MODEL_DIR/Qwen3.8-27B-Kairic-IU4-GDN-Output.pfs"
|
||||
|
||||
if [[ ! -x "$SERVER_BIN" ]]; then
|
||||
echo "missing runtime: $SERVER_BIN" >&2
|
||||
echo "fetch and extract it:" >&2
|
||||
echo " curl -fL -o /tmp/unsloth-llama.tar.gz https://github.com/unslothai/llama.cpp/releases/download/b11030-mix-5ff778e/app-b11030-mix-5ff778e-linux-x64-rocm-gfx1151.tar.gz" >&2
|
||||
echo " mkdir -p $RUNTIME_DIR && tar xzf /tmp/unsloth-llama.tar.gz -C $RUNTIME_DIR" >&2
|
||||
echo "ERROR: Kairic Edge runtime not found at $SERVER_BIN" >&2
|
||||
echo " Build it with: scripts/build-kairic-edge-gfx1151.sh" >&2
|
||||
exit 1
|
||||
fi
|
||||
|
||||
# Point -m at the FIRST split part, not a concatenated file: the parts
|
||||
# carry ggml.file_count=3 metadata in part 1's header, so even a
|
||||
# byte-correct concatenation still advertises itself as a 3-way split and
|
||||
# the loader rejects a non-split filename ("invalid split file name").
|
||||
# With -m on part 1, llama.cpp loads the 3-way split natively (parts 2-3
|
||||
# are auto-discovered in the same directory).
|
||||
MODEL_FILE="$MODEL_DIR/UD-IQ4_XS/Qwen3.8-Flash-Next-UD-IQ4_XS-00001-of-00003.gguf"
|
||||
if [[ ! -r "$MODEL_FILE" ]]; then
|
||||
echo "missing target model: $MODEL_FILE" >&2
|
||||
echo "fetch it: bash $SCRIPT_DIR/download-frank-large-unsloth.sh" >&2
|
||||
exit 1
|
||||
fi
|
||||
|
||||
# The MTP shared head borrows the token embedding and the output projection
|
||||
# from the main model at runtime. It must be passed explicitly with -md:
|
||||
# sidecar auto-discovery does not search the mtp/ subfolder, so
|
||||
# --spec-type draft-mtp on its own would find nothing and serve at the
|
||||
# main model's speed with no error saying why.
|
||||
MTP_FILE="$MODEL_DIR/mtp/mtp-Qwen3.8-Flash-Next-shared-Q8_0.gguf"
|
||||
if [[ "$ENABLE_MTP" == "1" && ! -r "$MTP_FILE" ]]; then
|
||||
echo "missing MTP head: $MTP_FILE" >&2
|
||||
echo "fetch and assemble it: bash $SCRIPT_DIR/download-frank-large-unsloth.sh" >&2
|
||||
exit 1
|
||||
fi
|
||||
|
||||
# The Qwen3.8 family template keeps prior thinking blocks across turns when
|
||||
# preserve_thinking is set; pass --jinja and the kwarg so multi-turn agents
|
||||
# do not lose the trail. A request-level chat_template_kwargs still wins.
|
||||
# The template gates reasoning_effort to {xhigh, medium, low} — the harness
|
||||
# folds its levels onto that set in models.yml (reasoningEffortMap).
|
||||
ARGS=(
|
||||
-m "$MODEL_FILE"
|
||||
-c "$CONTEXT_SIZE"
|
||||
-np "$PARALLEL_SLOTS"
|
||||
-ngl 999
|
||||
--jinja
|
||||
--alias frank-large
|
||||
--host "$HOST"
|
||||
--port "$PORT"
|
||||
--chat-template-kwargs '{"preserve_thinking":true}'
|
||||
)
|
||||
if [[ "$ENABLE_MTP" == "1" ]]; then
|
||||
ARGS+=(-md "$MTP_FILE" --spec-type draft-mtp --spec-draft-n-max "$SPEC_DRAFT_N_MAX")
|
||||
fi
|
||||
if [[ "$ENABLE_VISION" == "1" ]]; then
|
||||
MMPROJ_FILE="$MODEL_DIR/vision/mmproj-F16.gguf"
|
||||
if [[ ! -r "$MMPROJ_FILE" ]]; then
|
||||
echo "missing projector: $MMPROJ_FILE" >&2
|
||||
echo "fetch and assemble it: bash $SCRIPT_DIR/download-frank-large-unsloth.sh" >&2
|
||||
for f in "$MODEL_FILE" "$FFN_SIDECAR" "$GDN_SIDECAR" "$GDN_OUTPUT_SIDECAR"; do
|
||||
if [[ ! -r "$f" ]]; then
|
||||
echo "ERROR: missing asset: $f" >&2
|
||||
echo " Fetch it with: scripts/download-frank-large-kairic.sh" >&2
|
||||
exit 1
|
||||
fi
|
||||
ARGS+=(--mmproj "$MMPROJ_FILE")
|
||||
done
|
||||
|
||||
# --- PromptForge env block (the Kairic Edge runner's exact env) ----------
|
||||
export HIP_VISIBLE_DEVICES=0
|
||||
export HSA_OVERRIDE_GFX_VERSION=11.5.1
|
||||
export LD_LIBRARY_PATH="/opt/rocm/lib:/opt/rocm/llvm/lib:${LD_LIBRARY_PATH:-}"
|
||||
export GGML_CUDA_GRAPH_OPT=0
|
||||
# Fast-greedy mode (0) rejects sampling/tools/a reasoning budget; compatibility
|
||||
# mode (1) enables them. The harness needs all three, so default to 1.
|
||||
if [[ "$COMPATIBILITY_MODE" == "1" ]]; then
|
||||
export LLAMA_TARGET_GREEDY_ARGMAX_FASTPATH=0
|
||||
export PROMPTFORGE_OUTPUT_K8_STRICT_GREEDY=0
|
||||
else
|
||||
export LLAMA_TARGET_GREEDY_ARGMAX_FASTPATH=1
|
||||
export PROMPTFORGE_OUTPUT_K8_STRICT_GREEDY=1
|
||||
fi
|
||||
export LLAMA_MTP_CPU_ARGMAX_FASTPATH=1
|
||||
export PROMPTFORGE_TARGET_ONLY=0
|
||||
export PROMPTFORGE_MODE=iu4_ffn
|
||||
export PROMPTFORGE_IU4_SIDECAR="$FFN_SIDECAR"
|
||||
export PROMPTFORGE_SIDECAR="$FFN_SIDECAR"
|
||||
export PROMPTFORGE_IU4_HADAMARD=1
|
||||
export PROMPTFORGE_IU4_SEGMENTED=0
|
||||
export PROMPTFORGE_ENABLE_FFN_KEEPERS=0
|
||||
export PROMPTFORGE_FFN_KEEPERS=late6
|
||||
export PROMPTFORGE_ENABLE_GDN=1
|
||||
export PROMPTFORGE_ENABLE_GDN_W8=0
|
||||
export PROMPTFORGE_GDN_SIDECAR_OVERRIDE=1
|
||||
export PROMPTFORGE_GDN_SIDECAR="$GDN_SIDECAR"
|
||||
export PROMPTFORGE_GDN_IU4_HADAMARD=1
|
||||
export PROMPTFORGE_ENABLE_GDN_KEEPERS=0
|
||||
export PROMPTFORGE_ENABLE_GDN_OUTPUT=1
|
||||
export PROMPTFORGE_GDN_OUTPUT_SIDECAR="$GDN_OUTPUT_SIDECAR"
|
||||
export PROMPTFORGE_GDN_OUTPUT_KEEPERS=v3_lateq6
|
||||
export PROMPTFORGE_ENABLE_SMALLM_IU4=1
|
||||
export PROMPTFORGE_ENABLE_SMALLM_GDN_IU4=1
|
||||
export PROMPTFORGE_ENABLE_SMALLM_GDN_OUTPUT_IU4=0
|
||||
export PROMPTFORGE_ENABLE_IU4_DECODE_M2_M5=0
|
||||
|
||||
# --- the serve command (the Kairic Edge runner's flags, fleet-adapted) ----
|
||||
ARGS=(
|
||||
-m "$MODEL_FILE" --alias frank-large
|
||||
--host "$HOST" --port "$PORT" --jinja
|
||||
--chat-template-kwargs '{"preserve_thinking":true}'
|
||||
-dev ROCm0 -ngl 999
|
||||
-c "$CONTEXT_SIZE" -b 2048 -ub 512 -fa on -ctk f16 -ctv f16
|
||||
-t 16 -tb 32 -np "$PARALLEL_SLOTS" -ctxcp 32 --cache-ram "$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 f16 --spec-draft-type-v f16
|
||||
--spec-draft-n-max "$SPEC_DRAFT_N_MAX" --spec-draft-n-min 0
|
||||
--spec-draft-p-min 0.0 --spec-draft-p-split 0.10
|
||||
--spec-draft-backend-sampling
|
||||
--temp 0 --top-p 1.0 --top-k 0 --min-p 0.0
|
||||
--reasoning auto --reasoning-format deepseek --reasoning-budget -1
|
||||
)
|
||||
|
||||
exec "$SERVER_BIN" "${ARGS[@]}"
|
||||
|
||||
+63
-41
@@ -1,16 +1,18 @@
|
||||
#!/usr/bin/env bats
|
||||
# Seam: the frank-large unsloth-llama.cpp root unit on dankclaw.
|
||||
# Seam: the frank-large Kairic Edge root unit on dankclaw.
|
||||
#
|
||||
# The 2026-09-21 cutover moved this service from the CIRU v4.4.1 runtime
|
||||
# (jcbtc/Qwen3.8-Flash-CIRU-STRIX-Orca) onto the unsloth llama.cpp prebuilt
|
||||
# (b11030-mix-5ff778e, ROCm gfx1151) serving
|
||||
# unsloth/Qwen3.8-Flash-Next-GGUF:UD-IQ4_XS, still as a ROOT unit: a
|
||||
# prebuilt tarball with its own bundled ROCm has no container image to
|
||||
# install and no generated unit to dodge. This seam pins what a flag list
|
||||
# cannot show: the operator's one-stream / 200k shape, the payload the
|
||||
# serve script refuses to start without, the explicit -md MTP wiring
|
||||
# (sidecar auto-discovery does not search the mtp/ subfolder), a deploy
|
||||
# handler that gates on the port, and the fact that the sweep for a stray
|
||||
# The 2026-09-21 cutover moved this service from the unsloth llama.cpp
|
||||
# prebuilt (b11030-mix-5ff778e, ROCm gfx1151) serving
|
||||
# unsloth/Qwen3.8-Flash-Next-GGUF:UD-IQ4_XS onto the Kairic Edge runtime
|
||||
# (ciru-ai/ROCmFPX, branch kairic-edge-qwen38-27b-v1.2, commit 205a3e5)
|
||||
# serving jcbtc/Qwen3.8-27B-IU4-Kairic-Edge, still as a ROOT unit: a
|
||||
# source-built runtime has no container image to install and no generated
|
||||
# unit to dodge. This seam pins what a flag list cannot show: the
|
||||
# operator's one-stream / full-window shape, the payload the serve script
|
||||
# refuses to start without, the MTP + n-gram spec wiring (DFlash is NOT
|
||||
# available for this model), compatibility mode (the harness needs
|
||||
# sampling/tools/reasoning, which fast-greedy rejects), a deploy handler
|
||||
# that gates on the port, and the fact that the sweep for a stray
|
||||
# benchmark run cannot take frank-small down with it.
|
||||
|
||||
load helpers
|
||||
@@ -18,13 +20,15 @@ load helpers
|
||||
ENV_FILE="$REPO_ROOT/scripts/frank-large.env"
|
||||
UNIT="$REPO_ROOT/scripts/frank-large.service"
|
||||
SERVE="$REPO_ROOT/scripts/serve-frank-large.sh"
|
||||
FETCH="$REPO_ROOT/scripts/download-frank-large-unsloth.sh"
|
||||
FETCH="$REPO_ROOT/scripts/download-frank-large-kairic.sh"
|
||||
BUILD="$REPO_ROOT/scripts/build-kairic-edge-gfx1151.sh"
|
||||
REMOTE_DEPLOY="$REPO_ROOT/scripts/deploy-remote.sh"
|
||||
|
||||
@test "the frank-large unit, env and serve files exist where the deployer installs them from" {
|
||||
@test "the frank-large unit, env, serve and build files exist where the deployer installs them from" {
|
||||
[ -f "$ENV_FILE" ]
|
||||
[ -f "$UNIT" ]
|
||||
[ -x "$SERVE" ]
|
||||
[ -f "$BUILD" ]
|
||||
}
|
||||
|
||||
@test "frank-large is boot-persistent, self-healing and unprivileged" {
|
||||
@@ -40,61 +44,79 @@ REMOTE_DEPLOY="$REPO_ROOT/scripts/deploy-remote.sh"
|
||||
grep -q 'FRANK_LARGE_ENV_FILE=/home/dank/serverAppConfigs/scripts/frank-large.env' "$UNIT"
|
||||
}
|
||||
|
||||
@test "the operator's shape is one stream of 200k context with MTP on" {
|
||||
@test "the operator's shape is one stream of the full 262144 window with MTP depth 4" {
|
||||
local ctx slots
|
||||
ctx="$(sed -nE 's/^CONTEXT_SIZE=([0-9]+)$/\1/p' "$ENV_FILE")"
|
||||
slots="$(sed -nE 's/^PARALLEL_SLOTS=([0-9]+)$/\1/p' "$ENV_FILE")"
|
||||
# 200000 is the operator's requested serving shape (2026-09-21); the
|
||||
# model's trained window is 262144.
|
||||
[ "$ctx" -eq 200000 ]
|
||||
# 262144 is the model's native window (the operator's call, 2026-09-21).
|
||||
[ "$ctx" -eq 262144 ]
|
||||
# One stream.
|
||||
[ "$slots" -eq 1 ]
|
||||
grep -q '^ENABLE_MTP=1$' "$ENV_FILE"
|
||||
# MTP depth 4 (the model's MTP layers) + n-gram drafting (24/64/64).
|
||||
grep -q '^SPEC_DRAFT_N_MAX=4$' "$ENV_FILE"
|
||||
}
|
||||
|
||||
@test "frank-large stays text-only until the projector is enabled" {
|
||||
grep -q '^ENABLE_VISION=0$' "$ENV_FILE"
|
||||
# The fleet's image path is frank-small; the projector is on disk and is
|
||||
# one env flip away, but models.yml declares frank-large text-only.
|
||||
@test "the harness needs compatibility mode (sampling, tools, reasoning)" {
|
||||
# The fast-greedy path rejects sampling, penalties, probabilities,
|
||||
# grammar-constrained tool calls, logit bias, LoRA and a reasoning
|
||||
# budget. The harness needs all three, so COMPATIBILITY_MODE=1.
|
||||
grep -q '^COMPATIBILITY_MODE=1$' "$ENV_FILE"
|
||||
# The serve script enables the fastpath off in compatibility mode.
|
||||
grep -q 'LLAMA_TARGET_GREEDY_ARGMAX_FASTPATH=0' "$SERVE"
|
||||
}
|
||||
|
||||
@test "frank-large stays text-only" {
|
||||
# The Kairic Edge model is text-only (no vision projector). The fleet's
|
||||
# image path is frank-small; models.yml declares frank-large text-only.
|
||||
! grep -q -- '--mmproj' "$SERVE"
|
||||
grep -q -- '--mmproj' "$REPO_ROOT/scripts/serve-frank-small.sh"
|
||||
}
|
||||
|
||||
@test "the serve script pins the prebuilt runtime and refuses a missing build" {
|
||||
grep -q 'unsloth-llama-b11030' "$SERVE"
|
||||
@test "the serve script pins the Kairic Edge runtime and refuses a missing build" {
|
||||
grep -q 'ROCmFPX-kairic' "$SERVE"
|
||||
grep -q 'llama-server' "$SERVE"
|
||||
# A missing runtime or payload is a deploy error with a pointer, not a
|
||||
# restart loop.
|
||||
grep -q 'missing runtime' "$SERVE"
|
||||
grep -q 'missing target model' "$SERVE"
|
||||
grep -q 'missing MTP head' "$SERVE"
|
||||
grep -q 'Kairic Edge runtime not found' "$SERVE"
|
||||
grep -q 'missing asset' "$SERVE"
|
||||
# The Qwen3.8 template keeps prior thinking blocks across turns only
|
||||
# when the kwarg is set.
|
||||
grep -q 'preserve_thinking' "$SERVE"
|
||||
}
|
||||
|
||||
@test "the serve script wires the MTP head explicitly and speculates" {
|
||||
# Sidecar auto-discovery does not search the mtp/ subfolder, so the head
|
||||
# must be passed with -md or the server runs at the main model's speed
|
||||
# with no error saying why.
|
||||
grep -q -- '-md "$MTP_FILE"' "$SERVE"
|
||||
@test "the serve script wires the MTP + n-gram spec method and the sidecars" {
|
||||
# The Kairic Edge model uses native MTP depth 4 + n-gram drafting
|
||||
# (24/64/64). DFlash is NOT available for this model (no DRAFT_DFLASH
|
||||
# spec type in the Kairic Edge runtime).
|
||||
grep -q -- '--spec-type draft-mtp' "$SERVE"
|
||||
grep -q 'mtp-Qwen3.8-Flash-Next-shared-Q8_0.gguf' "$SERVE"
|
||||
grep -q -- '--kairic-edge' "$SERVE"
|
||||
grep -q -- '--spec-draft-n-max' "$SERVE"
|
||||
# The three PromptForge sidecars (FFN, GDN, GDN-Output) are wired via
|
||||
# the PROMPTFORGE_* env block.
|
||||
grep -q 'PROMPTFORGE_IU4_SIDECAR' "$SERVE"
|
||||
grep -q 'PROMPTFORGE_GDN_SIDECAR' "$SERVE"
|
||||
grep -q 'PROMPTFORGE_GDN_OUTPUT_SIDECAR' "$SERVE"
|
||||
}
|
||||
|
||||
@test "the payload is fetched resumably and verified against the live Hub tree" {
|
||||
grep -q 'unsloth/Qwen3.8-Flash-Next-GGUF' "$FETCH"
|
||||
@test "the payload is fetched resumably and verified against declared sizes + sha256" {
|
||||
grep -q 'jcbtc/Qwen3.8-27B-IU4-Kairic-Edge' "$FETCH"
|
||||
grep -q -- '-fL -C -' "$FETCH"
|
||||
# The LFS oids come from the Hub tree API at verify time, not from a
|
||||
# file that could drift; each part's local sha256 is compared to its
|
||||
# oid and a mismatch fails the run.
|
||||
grep -q 'tree/main' "$FETCH"
|
||||
# Each file's local sha256 is compared to its declared oid and a
|
||||
# mismatch fails the run.
|
||||
grep -q 'SHA256 MISMATCH' "$FETCH"
|
||||
}
|
||||
|
||||
@test "the build script pins the Kairic Edge commit and the CK patch" {
|
||||
grep -q 'fdf4bb7fcc984811cef48ce817d89aac064b984a' "$BUILD"
|
||||
grep -q 'composable-kernel-gfx1151-iu4.patch' "$BUILD"
|
||||
grep -q 'gfx1151' "$BUILD"
|
||||
}
|
||||
|
||||
@test "the fleet endpoint and alias survive the cutover" {
|
||||
grep -q '^HOST=0.0.0.0$' "$ENV_FILE"
|
||||
grep -q '^PORT=7770$' "$ENV_FILE"
|
||||
grep -q '^MODEL_DIR=/home/dank/models/Qwen3.8-Flash-Next-UD-IQ4_XS$' "$ENV_FILE"
|
||||
grep -q '^MODEL_DIR=/home/dank/models/Qwen3.8-27B-IU4-Kairic-Edge$' "$ENV_FILE"
|
||||
grep -q -- '--alias frank-large' "$SERVE"
|
||||
}
|
||||
|
||||
@test "the deploy handler retires the halogen quadlet without deleting it" {
|
||||
@@ -116,7 +138,7 @@ REMOTE_DEPLOY="$REPO_ROOT/scripts/deploy-remote.sh"
|
||||
# frank-small on this host is ALSO a llama-server. The sweep must match
|
||||
# the model path, not the binary name, or a frank-large deploy restarts
|
||||
# the 3090 endpoint.
|
||||
grep -q "pkill -f 'Qwen3.8-Flash-Next-UD-IQ4_XS'" "$REMOTE_DEPLOY"
|
||||
grep -q "pkill -f 'Qwen3.8-27B-IU4-Kairic-Edge'" "$REMOTE_DEPLOY"
|
||||
# ...and only inside the large handler: extract it and check there is no
|
||||
# bare binary-name pkill in it.
|
||||
local large
|
||||
|
||||
Reference in New Issue
Block a user