# Tunables for frank-default-small (ornith-ai/Ornith-1.5-35B-A3B-FP8,
# qwen3_5_moe hybrid MoE, Dankserver, RTX 3090).
#
# Runtime: FreeToken v0.1.2 (edge-native MoE serving engine).
# Installed via uv into /home/dank/freetoken/.venv (CPython 3.12).
# FreeToken keeps expert weights in host RAM with an LRU GPU cache;
# KV is paged with radix prefix sharing.  Only the full-attention
# layers page KV (~20 KiB/token); the GDN layers use constant-size
# per-sequence state (mamba slot pool).
#
# Model: ornith-ai/Ornith-1.5-35B-A3B-FP8 (HuggingFace safetensors,
# compressed-tensors FP8, ~35 GB on disk).  Ornith-1.5 is a
# self-improvement RL-trained coding/agentic model built on Qwen3.5 +
# Gemma4; ~35B total / ~3B active (A3B), same qwen3_5_moe arch and the
# same ~35 GB FP8 weight mass as the Huihui FP8 it replaces, so the
# FreeToken memory/pool plan carries unchanged.  Native 262144 context.
# Reasoning model: each assistant turn opens with a <think> block,
# surfaced separately via the qwen3 reasoning parser (REASONING=on).
# The RTX 3090 has no FP8 tensor cores, so FP8 runs via upcast (as
# Huihui did).  Replaced batsclamp/Huihui-Qwen3.6-35B-A3B-abliterated-
# FP8 on 2026-09-01.
#
# RISK: this is compressed-tensors PER-CHANNEL FP8 (weights strategy
# "channel"), the one FP8 layout the runbook flags as a FreeToken v0.1.2
# loader bug.  Load is being verified live; 37 GB fits RAM so a failure is
# a clean crash-loop, not a swap-thrash.  The BF16 sibling
# (ornith-ai/Ornith-1.5-35B-A3B, ~70 GB) does NOT fit this 62 GB box —
# never fall back to it (that is the 2026-09-01 Thomson outage mode).
#
# Chat template: the checkpoint's stock Qwen template is WRONG for this
# model (its own model card says so and ships a modified
# chat_template.jinja for the agentic benchmarks).  The fleet standard is
# the Qwen-Sharp template (scripts/chat-template.jinja, repo-tracked and
# shared with frank-default-large) — see CHAT_TEMPLATE_FILE below.
#
# Pool sizing: GPU budget (~17.6 GiB after weights + fixed caches) is
# split MoE-first.  MOE_CACHE_SIZE pins resident expert slots; NUM_TOKENS
# pins the KV pool.  At 2048 slots / 453005 tokens the split is ~20%
# residency and ~8.6 GiB KV.  Live resize via
# `ft ctl cache --kv N --moe M` can grow KV by shrinking MoE without
# restart (the reverse requires a restart).
#
# WARNING: do not name any variable TEMP, HOST, or GPU_MAX_HEAP_SIZE.
# The ROCm HIP runtime reads those bare env vars (see the 2026-08-13 TEMP
# incident).  This box is NVIDIA/CUDA, but the rule keeps the env portable.

# Model directory (safetensors checkpoint, ~35 GB, compressed-tensors FP8).
MODEL_DIR=/home/dank/models/ornith-1.5-35b-a3b-fp8

# Chat template: the fleet Qwen-Sharp template (repo-tracked), shared with
# frank-default-large.  The checkpoint's stock template mis-serializes
# reasoning for this model; the Sharp template renders the <think> trail and
# the Qwen3.5-family tool-call shape correctly.
CHAT_TEMPLATE_FILE=/home/dank/serverAppConfigs/scripts/chat-template.jinja

# FreeToken venv (uv-managed CPython 3.12, ft CLI, flashinfer, torch+cu130).
FT_VENV=/home/dank/freetoken/.venv
CUDA_HOME_DIR=/home/dank/freetoken/.venv/lib/python3.12/site-packages/nvidia/cu13

ALIAS=frank-default-small
BIND_ADDR=0.0.0.0
LISTEN_PORT=7770

# Expert residency: 2048 of 10240 total expert instances (20%).
# Each slot ~3 MiB → ~6.0 GiB VRAM for the MoE cache.
MOE_CACHE_SIZE=2048

# KV pool: 453005 tokens (~8.6 GiB at ~20 KiB/token).
# Covers 4 concurrent sessions at ~113k unique context each
# (more with radix prefix sharing for common prefixes).
NUM_TOKENS=453005

# Max concurrent decoding requests (also caps mamba slot allocation).
MAX_RUNNING_REQUESTS=4