# 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.
#
# 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.
MODEL_DIR=/home/dank/models/Qwen3.8-27B-UD-Q8_K_XL

# 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 prior deployments served, so
# no client, probe or models.yml entry changes address.
HOST=0.0.0.0
PORT=7770

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

# 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

# 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