# frank-large — CIRU v4.4.1 (QSA window hotfix) serving
# jcbtc/Qwen3.8-Flash-CIRU-STRIX-Orca on the Strix Halo iGPU (gfx1151).
#
# These are the launcher tunables read by the runtime's
# scripts/ciru/run-orca-server.sh (see the serve script). The 36-variable
# kernel bundle and the PLE pager defaults live in the runtime's own
# profiles/strix-halo-production.env, which the launcher sources AFTER this
# file; every profile line is a ${VAR:-default}, so a value set here wins.
#
# 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 launcher itself consumes it for --host; its value doubles as a
# JIT-cache directory name, which is why 0.0.0.0 is safe.

# The assembled payload (scripts/download-frank-large-orca.sh): the launcher
# refuses to start without the main GGUF, the MTP head and the PLE sidecar.
MODEL_DIR=/home/dank/models/Qwen3.8-Flash-CIRU-STRIX-Orca

# Fleet endpoint: the same port and alias the halogen predecessor served, so
# no client, probe or models.yml entry changes address.
HOST=0.0.0.0
PORT=7770

# One stream, full context (operator call, 2026-09-19). MTP requires exactly
# one slot in this runtime, so the drafter's constraint and the operator's
# ask are the same number. 262144 is the model's trained window; the GGUF
# carries no rope scaling.
CONTEXT_SIZE=262144
PARALLEL_SLOTS=1

# MTP head: on. Depth 4 is the Orca variant's own default (mtp_depth_default
# in the launcher); the sidecar is the Q8_0 MTP file from the model repo.
ENABLE_MTP=1

# Text-only for now: the F16 projector is on disk at
# vision/mmproj-Qwen3.8-Flash-Orca-F16.mmproj; 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

# PLE pager: the 52.4 GiB payload is mmap'd and paged by the engine's own
# workers; this is the hot window kept resident. The vendor's production
# profile default is 4096.
PLE_CACHE_MIB=4096