# 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.
#
# 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.
#
# DO NOT name a new tunable TEMP, HOST or GPU_MAX_HEAP_SIZE: the HIP
# 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 prebuilt runtime (see the serve script for the fetch line).
RUNTIME_DIR=/home/dank/GitPackages/unsloth-llama-b11030

# Fleet endpoint: the same port and alias the CIRU 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
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

# 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