# frank-large — gufo (gufo-org/gufo) serving
# Swift-1.5-Qwen3.8-27B-Uncensored (abliterated) 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 target payload (scripts/download-frank-large-swift.sh): the serve
# script refuses to start without the main GGUF and the DFlash2 drafter.
# Swapped in from unsloth/Qwen3.8-27B-GGUF:UD-Q8_K_XL on 2026-09-28. The two
# are structurally interchangeable for gufo (same qwen35 architecture, the
# same 866 tensors in the same order, the same per-tensor Q8_0/F32/BF16
# layout, the same MTP head), so only this path changed.
MODEL_DIR=/home/dank/models/Swift-1.5-Qwen3.8-27B-Uncensored-MTP-UD-Q8_K_XL
MODEL_FILE=/home/dank/models/Swift-1.5-Qwen3.8-27B-Uncensored-MTP-UD-Q8_K_XL/Swift-1.5-Qwen3.8-27B-Uncensored-Dynamic-MTP-UD-Q8_K_XL.gguf

# The DFlash2 drafter is UNCHANGED by the model swap and still lives beside
# the previous target, so it carries its own directory. It has a sliding
# window of 2048, which is what keeps its KV small (~40 MiB).
DRAFTER_DIR=/home/dank/models/Qwen3.8-27B-UD-Q8_K_XL
DRAFTER_FILE=/home/dank/models/Qwen3.8-27B-UD-Q8_K_XL/Qwen3.8-27B-DFlash2-Q4_K_M.gguf

# 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 frank-large has 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