frank-large: swap to stock llama.cpp serving Qwen3.8-27B UD-Q8_K_XL with DFlash2
Replace the Kairic Edge ROCmFPX build with the unsloth b11030 stock llama.cpp prebuilt (ROCm gfx1151) serving unsloth/Qwen3.8-27B-GGUF: UD-Q8_K_XL (a 27B dense model, 31.5 GiB) with the z-lab DFlash2 Q4_K_M drafter (depth 4) on the gfx1151 iGPU. Serving shape: one 262,144-token conversation, q8_0 KV (the build lacks fp8), text-only, greedy sampling, Qwen-Sharp v22.4.0 template. - scripts/serve-frank-large.sh: stock llama.cpp + DFlash2 spec decode - scripts/frank-large.env: new model/drafter/runtime, 262144 ctx / 1 slot - scripts/download-frank-large.sh: per-file fetch, verify mode, idempotent - scripts/frank-large.service: updated description - scripts/deploy-remote.sh: updated pkill pattern + asset gates - tests/frank_large_unit.bats: new model/runtime/spec assertions - docs: new runbook (active), Kairic Edge runbook retired (rollback target) Co-Authored-By: Claude <noreply@anthropic.com>
This commit is contained in:
FrankandClaude committed
1 parent
43b8258061
commit
7689092db8
10 files changed
+414
-306
No files matched your search
+15
-16
@@ -1072,21 +1072,20 @@ deploy_anubis() {
|
||||
wait_container_healthy anubis 60 || return 1
|
||||
}
|
||||
|
||||
# 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.
|
||||
# frank-large is the stock llama.cpp prebuilt (unsloth b11030, ROCm
|
||||
# gfx1151) serving unsloth/Qwen3.8-27B-GGUF:UD-Q8_K_XL with the DFlash2
|
||||
# drafter (z-lab/Qwen3.8-27B-DFlash2-GGUF:Q4_K_M) on the Strix Halo iGPU,
|
||||
# as a ROOT unit since the 2026-09-19 cutover: the runtime is a prebuilt
|
||||
# binary, 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 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="${LLM_LARGE_MODEL:-/home/dank/models/Qwen3.8-27B-IU4-Kairic-Edge/Qwen3.8-27B-IU4-Kairic-Edge.gguf}"
|
||||
LLM_LARGE_DRAFT="${LLM_LARGE_DRAFT:-/home/dank/models/Qwen3.8-27B-IU4-Kairic-Edge/Qwen3.8-27B-Kairic-IU4-FFN.pfs}"
|
||||
# It replaces the Kairic Edge runtime (ciru-ai/ROCmFPX), which had
|
||||
# replaced the unsloth llama.cpp prebuilt serving
|
||||
# unsloth/Qwen3.8-Flash-Next-GGUF:UD-IQ4_XS. The port gate is the same as
|
||||
# every cutover since 2026-09-16: nothing starts until 7770 is released.
|
||||
LLM_LARGE_MODEL="${LLM_LARGE_MODEL:-/home/dank/models/Qwen3.8-27B-UD-Q8_K_XL/Qwen3.8-27B-UD-Q8_K_XL.gguf}"
|
||||
LLM_LARGE_DRAFT="${LLM_LARGE_DRAFT:-/home/dank/models/Qwen3.8-27B-UD-Q8_K_XL/Qwen3.8-27B-DFlash2-Q4_K_M.gguf}"
|
||||
|
||||
retire_halogen_large_quadlet() {
|
||||
local trash="$HOME/.AGENTTRASH/20260919-orca-cutover/quadlet"
|
||||
@@ -1126,7 +1125,7 @@ deploy_llm_large() {
|
||||
for f in "$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-kairic.sh" >&2
|
||||
echo "frank-large: fetch it: bash scripts/download-frank-large.sh" >&2
|
||||
missing=1
|
||||
fi
|
||||
done
|
||||
@@ -1141,7 +1140,7 @@ 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 'Qwen3.8-27B-IU4-Kairic-Edge' 2>/dev/null || true
|
||||
pkill -f 'Qwen3.8-27B-UD-Q8_K_XL' 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
|
||||
|
||||
@@ -1,110 +0,0 @@
|
||||
#!/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: $MODEL_DIR"
|
||||
Executable
+89
@@ -0,0 +1,89 @@
|
||||
#!/usr/bin/env bash
|
||||
# Download the frank-large payload on Dankclaw:
|
||||
# - unsloth/Qwen3.8-27B-GGUF:UD-Q8_K_XL (the 27B dense main GGUF)
|
||||
# - z-lab/Qwen3.8-27B-DFlash2-GGUF:Q4_K_M (the DFlash2 drafter)
|
||||
#
|
||||
# bash scripts/download-frank-large.sh
|
||||
# bash scripts/download-frank-large.sh --verify-only
|
||||
#
|
||||
# Integrity: every file is checked against its declared byte count and sha256
|
||||
# (the values below are the LFS oids from the Hub, 2026-09-21). An HF token
|
||||
# at ~/.cache/huggingface/token is used when present to clear the anonymous
|
||||
# rate limit on a 31 GB transfer.
|
||||
#
|
||||
# Layout after a successful run (MODEL_DIR):
|
||||
# Qwen3.8-27B-UD-Q8_K_XL.gguf 31457991680 main GGUF
|
||||
# Qwen3.8-27B-DFlash2-Q4_K_M.gguf 1143006816 DFlash2 drafter
|
||||
set -euo pipefail
|
||||
|
||||
MODEL_DIR="/home/dank/models/Qwen3.8-27B-UD-Q8_K_XL"
|
||||
|
||||
mode="download"
|
||||
[[ "${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 <url> <dest>
|
||||
local url="$1" dest="$2"
|
||||
[[ -s "$dest" ]] && return 0
|
||||
mkdir -p "$(dirname "$dest")"
|
||||
echo "fetching $dest"
|
||||
curl -fL -C - "${auth[@]}" --retry 5 --retry-delay 3 -o "$dest" "$url"
|
||||
}
|
||||
|
||||
# filename size sha256 url — the LFS oids from the Hub (2026-09-21)
|
||||
FILES=(
|
||||
"Qwen3.8-27B-UD-Q8_K_XL.gguf 31457991680 af36ecb6b5db1407953345b746c14ac93f0657dda413910b4348683a2d990377 https://huggingface.co/unsloth/Qwen3.8-27B-GGUF/resolve/main/Qwen3.8-27B-UD-Q8_K_XL.gguf"
|
||||
"Qwen3.8-27B-DFlash2-Q4_K_M.gguf 1143006816 1a25c56858e1ebe93f2718ac1d49d1151f9323325c1bbfd6209370f4db131ebd https://huggingface.co/z-lab/Qwen3.8-27B-DFlash2-GGUF/resolve/main/Qwen3.8-27B-DFlash2-Q4_K_M.gguf"
|
||||
)
|
||||
|
||||
# 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" <<'PY'
|
||||
import hashlib, os, sys
|
||||
model_dir = sys.argv[1]
|
||||
# (rel, size, sha256) triples — the LFS oids from the Hub (2026-09-21).
|
||||
specs = {
|
||||
"Qwen3.8-27B-UD-Q8_K_XL.gguf": (31457991680, "af36ecb6b5db1407953345b746c14ac93f0657dda413910b4348683a2d990377"),
|
||||
"Qwen3.8-27B-DFlash2-Q4_K_M.gguf": (1143006816, "1a25c56858e1ebe93f2718ac1d49d1151f9323325c1bbfd6209370f4db131ebd"),
|
||||
}
|
||||
ok = True
|
||||
for rel, (size, sha) in specs.items():
|
||||
dest = os.path.join(model_dir, 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 _ _ url <<<"$line"
|
||||
dl "$url" "$MODEL_DIR/$rel"
|
||||
done
|
||||
fi
|
||||
|
||||
echo "frank-large payload complete: $MODEL_DIR"
|
||||
+14
-20
@@ -1,6 +1,6 @@
|
||||
# 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).
|
||||
# frank-large — stock llama.cpp (mainline, the unsloth b11030 prebuilt)
|
||||
# serving unsloth/Qwen3.8-27B-GGUF:UD-Q8_K_XL 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.
|
||||
@@ -9,15 +9,14 @@
|
||||
# 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-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 payload (scripts/download-frank-large.sh): the serve script refuses to
|
||||
# start without the main GGUF and the DFlash2 drafter.
|
||||
MODEL_DIR=/home/dank/models/Qwen3.8-27B-UD-Q8_K_XL
|
||||
|
||||
# The Kairic Edge runtime (scripts/build-kairic-edge-gfx1151.sh).
|
||||
RUNTIME_DIR=/home/dank/GitPackages/ROCmFPX-kairic/build-kairic
|
||||
# The stock llama.cpp runtime (the unsloth b11030 prebuilt).
|
||||
RUNTIME_DIR=/home/dank/GitPackages/unsloth-llama-b11030
|
||||
|
||||
# Fleet endpoint: the same port and alias the unsloth predecessor served, so
|
||||
# Fleet endpoint: the same port and alias the prior deployments served, so
|
||||
# no client, probe or models.yml entry changes address.
|
||||
HOST=0.0.0.0
|
||||
PORT=7770
|
||||
@@ -26,17 +25,12 @@ PORT=7770
|
||||
CONTEXT_SIZE=262144
|
||||
PARALLEL_SLOTS=1
|
||||
|
||||
# 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).
|
||||
# DFlash2 spec decode (a block-diffusion drafter) at depth 4. The drafter
|
||||
# has a sliding window of 2048 (small draft KV, ~40 MiB).
|
||||
SPEC_DRAFT_N_MAX=4
|
||||
|
||||
# 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
|
||||
# Prompt-cache budget: 8 GiB. The model is a 27B hybrid (16 full attention
|
||||
# + 48 Gated DeltaNet linear attention); its DeltaNet state is smaller than
|
||||
# a primarily-DeltaNet model, so the fleet's 12.8 GiB DeltaNet floor does
|
||||
# not apply.
|
||||
CACHE_RAM=8192
|
||||
@@ -1,5 +1,5 @@
|
||||
[Unit]
|
||||
Description=Kairic Edge (ROCmFPX v1.2, gfx1151) Qwen3.8-27B IU4 W4A4 (dankclaw, frank-large, Strix Halo iGPU)
|
||||
Description=stock llama.cpp (unsloth b11030, ROCm gfx1151) Qwen3.8-27B UD-Q8_K_XL, DFlash2 spec decode, fp8 KV, 262144 ctx / 1 slot, root systemd unit (dankclaw, frank-large, Strix Halo iGPU)
|
||||
After=network-online.target
|
||||
Wants=network-online.target
|
||||
|
||||
@@ -7,10 +7,9 @@ Wants=network-online.target
|
||||
Type=simple
|
||||
User=dank
|
||||
Group=dank
|
||||
# The engine pins staging buffers and the PLE pager's hot window; keep the
|
||||
# memlock budget unbounded so an RLIMIT smaller than the pinned set cannot
|
||||
# fail the load. Parity with the halogen quadlet's Ulimit=memlock=-1:-1 and
|
||||
# the other LLM units on this fleet.
|
||||
# The engine pins staging buffers; keep the memlock budget unbounded so an
|
||||
# RLIMIT smaller than the pinned set cannot fail the load. Parity with the
|
||||
# other LLM units on this fleet.
|
||||
LimitMEMLOCK=infinity
|
||||
Environment="FRANK_LARGE_ENV_FILE=/home/dank/serverAppConfigs/scripts/frank-large.env"
|
||||
ExecStart=/home/dank/serverAppConfigs/scripts/serve-frank-large.sh
|
||||
|
||||
@@ -1,34 +1,32 @@
|
||||
#!/usr/bin/env bash
|
||||
# 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.
|
||||
# Serve unsloth/Qwen3.8-27B-GGUF:UD-Q8_K_XL as frank-large on
|
||||
# Dankclaw's Strix Halo iGPU (gfx1151), using stock llama.cpp
|
||||
# (mainline, the unsloth b11030 prebuilt).
|
||||
#
|
||||
# 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).
|
||||
# Runtime: /home/dank/GitPackages/unsloth-llama-b11030/llama-server
|
||||
# (mainline, ROCm gfx1151 prebuilt). The build supports the qwen3_5
|
||||
# architecture and the DFlash2 drafter (llama_model_qwen35,
|
||||
# llama_model_dflash, common_speculative_impl_draft_dflash).
|
||||
#
|
||||
# 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).
|
||||
# layers on the iGPU (--n-gpu-layers 999). The 27B dense model (31.46 GiB GGUF) + the
|
||||
# DFlash2 drafter (1.14 GiB) + q8_0 KV (~8.6 GiB) + compute buffers 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).
|
||||
# Spec method: DFlash2 (a block-diffusion drafter) at depth 4. The drafter
|
||||
# has a sliding window of 2048 (small draft KV, ~40 MiB).
|
||||
#
|
||||
# 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).
|
||||
# KV: q8_0 quantized (--cache-type-k q8_0 --cache-type-v q8_0). The unsloth b11030
|
||||
# build does not support fp8 KV (allowed: f32/f16/bf16/q8_0/q4_0/q4_1/iq4_nl/q5_0/
|
||||
# q5_1); q8_0 is the highest-precision 8-bit option and preserves the ~8 GiB footprint.
|
||||
#
|
||||
# Text-only (no mmproj) — matching the prior frank-large.
|
||||
#
|
||||
# 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).
|
||||
# do not lose the trail. 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.
|
||||
@@ -37,96 +35,72 @@ set -euo pipefail
|
||||
SCRIPT_DIR="$(cd -- "$(dirname -- "${BASH_SOURCE[0]}")" && pwd)"
|
||||
ENV_FILE="${FRANK_LARGE_ENV_FILE:-$SCRIPT_DIR/frank-large.env}"
|
||||
if [[ -f "$ENV_FILE" ]]; then
|
||||
# shellcheck disable=SC1090
|
||||
set -a
|
||||
source "$ENV_FILE"
|
||||
set +a
|
||||
fi
|
||||
|
||||
# --- defaults (used when the env file does not set them) ------------------
|
||||
: "${RUNTIME_DIR:=/home/dank/GitPackages/ROCmFPX-kairic/build-kairic}"
|
||||
: "${MODEL_DIR:=/home/dank/models/Qwen3.8-27B-IU4-Kairic-Edge}"
|
||||
: "${RUNTIME_DIR:=/home/dank/GitPackages/unsloth-llama-b11030}"
|
||||
: "${MODEL_DIR:=/home/dank/models/Qwen3.8-27B-UD-Q8_K_XL}"
|
||||
: "${HOST:=0.0.0.0}"
|
||||
: "${PORT:=7770}"
|
||||
: "${CONTEXT_SIZE:=262144}"
|
||||
: "${PARALLEL_SLOTS:=1}"
|
||||
: "${SPEC_DRAFT_N_MAX:=4}"
|
||||
: "${COMPATIBILITY_MODE:=1}"
|
||||
: "${CACHE_RAM:=8192}"
|
||||
TEMPLATE_FILE="${TEMPLATE_FILE:-$SCRIPT_DIR/../dankserver/frank-medium/qwen-sharp-v22.4.0.jinja}"
|
||||
|
||||
SERVER_BIN="$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"
|
||||
SERVER_BIN="$RUNTIME_DIR/llama-server"
|
||||
MODEL_FILE="$MODEL_DIR/Qwen3.8-27B-UD-Q8_K_XL.gguf"
|
||||
DRAFTER_FILE="$MODEL_DIR/Qwen3.8-27B-DFlash2-Q4_K_M.gguf"
|
||||
|
||||
if [[ ! -x "$SERVER_BIN" ]]; then
|
||||
echo "ERROR: Kairic Edge runtime not found at $SERVER_BIN" >&2
|
||||
echo " Build it with: scripts/build-kairic-edge-gfx1151.sh" >&2
|
||||
echo "runtime not found at $SERVER_BIN" >&2
|
||||
exit 1
|
||||
fi
|
||||
for f in "$MODEL_FILE" "$FFN_SIDECAR" "$GDN_SIDECAR" "$GDN_OUTPUT_SIDECAR"; do
|
||||
if [[ ! -r "$f" ]]; then
|
||||
echo "ERROR: missing asset: $f" >&2
|
||||
echo " Fetch it with: scripts/download-frank-large-kairic.sh" >&2
|
||||
for f in "$MODEL_FILE" "$DRAFTER_FILE"; do
|
||||
if [[ ! -f "$f" ]]; then
|
||||
echo "missing asset $f (run scripts/download-frank-large.sh)" >&2
|
||||
exit 1
|
||||
fi
|
||||
done
|
||||
|
||||
# --- PromptForge env block (the Kairic Edge runner's exact env) ----------
|
||||
# --- env (the unsloth build's ROCm setup) --------------------------------
|
||||
export HIP_VISIBLE_DEVICES=0
|
||||
export HSA_OVERRIDE_GFX_VERSION=11.5.1
|
||||
export LD_LIBRARY_PATH="/opt/rocm/lib:/opt/rocm/llvm/lib:${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="$GDN_OUTPUT_SIDECAR"
|
||||
export PROMPTFORGE_GDN_OUTPUT_KEEPERS=v3_lateq6
|
||||
export PROMPTFORGE_ENABLE_SMALLM_IU4=1
|
||||
export PROMPTFORGE_ENABLE_SMALLM_GDN_IU4=1
|
||||
export PROMPTFORGE_ENABLE_SMALLM_GDN_OUTPUT_IU4=0
|
||||
export PROMPTFORGE_ENABLE_IU4_DECODE_M2_M5=0
|
||||
|
||||
# --- the serve command (the Kairic Edge runner's flags, fleet-adapted) ----
|
||||
# --- the serve command ---------------------------------------------------
|
||||
ARGS=(
|
||||
-m "$MODEL_FILE" --alias frank-large
|
||||
--host "$HOST" --port "$PORT" --jinja
|
||||
--chat-template-kwargs '{"preserve_thinking":true}'
|
||||
--host "$HOST"
|
||||
--port "$PORT"
|
||||
--model "$MODEL_FILE"
|
||||
--alias frank-large
|
||||
--ctx-size "$CONTEXT_SIZE"
|
||||
--parallel "$PARALLEL_SLOTS"
|
||||
--n-gpu-layers 999
|
||||
--jinja
|
||||
--chat-template-file "$TEMPLATE_FILE"
|
||||
-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
|
||||
--chat-template-kwargs '{"preserve_thinking":true}'
|
||||
--cache-type-k q8_0
|
||||
--cache-type-v q8_0
|
||||
--cache-ram "$CACHE_RAM"
|
||||
# DFlash2 spec decode (a block-diffusion drafter)
|
||||
--spec-type draft-dflash
|
||||
--model-draft "$DRAFTER_FILE"
|
||||
--spec-draft-n-max "$SPEC_DRAFT_N_MAX"
|
||||
--spec-draft-n-min 0
|
||||
--spec-draft-device ROCm0
|
||||
# Greedy sampling (the DFlash2 drafter needs greedy verification)
|
||||
--temp 0
|
||||
--top-p 1.0
|
||||
--top-k 0
|
||||
--min-p 0.0
|
||||
# Reasoning (thoughts land in reasoning_content)
|
||||
--reasoning auto
|
||||
--reasoning-format deepseek
|
||||
--reasoning-budget -1
|
||||
)
|
||||
|
||||
exec "$SERVER_BIN" "${ARGS[@]}"
|
||||
Reference in new issue
Block a user