# Tunables for frank-default-small (Qwen3.6-35B-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 10 full-attention
# layers page KV (~20 KiB/token); the 30 GDN layers use constant-size
# per-sequence state (mamba slot pool).
#
# Model: Qwen/Qwen3.6-35B-A3B-FP8 (HuggingFace safetensors, modelopt
# block-fp8 quant, 128x128 weight_block_size, 35 GB on disk).
# Architecture: qwen3_5_moe — 40 layers (10 attention + 30 GDN),
# 256 experts / 8 used, 2 KV heads × 256 dim, full_attention_interval=4.
#
# Replaced the llama.cpp Tiel-Coder-35B-A3B (UD-Q6_K_XL) deployment on
# 2026-09-02.  The old serve script and env are in .AGENTTRASH/.
#
# 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 (2048/10240) 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).
MODEL_DIR=/home/dank/models/qwen36-35b-a3b-fp8

# 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