# frank-large — gufo (gufo-org/gufo) 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.
#
# 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 payload (scripts/download-frank-large.sh): the serve script refuses to
# start without the main GGUF and the DFlash2 drafter. Both files are the
# same ones the llama.cpp deployment used — the cutover changed the RUNTIME,
# not the weights.
MODEL_DIR=/home/dank/models/Qwen3.8-27B-UD-Q8_K_XL

# The gufo runtime, built from source by scripts/build-gufo.sh.
RUNTIME_DIR=/home/dank/GitPackages/gufo-v0.1.1

# Fleet endpoint: the same port and alias every prior frank-large served, so
# no client, probe or models.yml entry changes address.
ALIAS=frank-large
HOST=0.0.0.0
PORT=7770

# One session, full 262144 context (the model's native window).
CONTEXT_SIZE=262144
SESSIONS=1

# DFlash2 spec decode (a block-diffusion drafter). gufo sizes the draft
# block itself; DRAFT_TOKENS caps the proposals per step (gufo's default is
# 7, chosen over llama.cpp's fixed depth 4 because gufo's adaptive policy
# shortens the block when acceptance drops) and DRAFT_POLICY is the block
# length controller.
DRAFT_TOKENS=7
DRAFT_POLICY=adaptive