# 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).
#
# 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-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 Kairic Edge runtime (scripts/build-kairic-edge-gfx1151.sh).
RUNTIME_DIR=/home/dank/GitPackages/ROCmFPX-kairic/build-kairic

# Fleet endpoint: the same port and alias the unsloth predecessor 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

# 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_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
# not apply.
CACHE_RAM=8192