# Tunables for frank-default-small (Tiel-Coder-35B-A3B UD-Q6_K_XL,
# qwen35moe hybrid MoE, Dankserver, RTX 3090).
#
# Runtime: upstream llama.cpp (latest master, CUDA build with
# -DGGML_CUDA_FA_ALL_QUANTS=ON -DCMAKE_CUDA_ARCHITECTURES=86) on RTX 3090
# 24 GB; Ryzen 7 7700X; 62 GB RAM.  Replaced the ik_llama.cpp Ornith
# CRACK Q8_0 deployment on 2026-09-01.
#
# Model: peculiar-ragdoll/Tiel-Coder-35B-A3B-GGUF, UD-Q6_K_XL quant
# (30 GB).  Architecture: qwen35moe — 40 layers, full_attention_interval=4
# (10 attention + 30 SSM/Mamba), 256 experts / 8 used, 2 KV heads × 256
# dim, embedding 2048, rope dimension_count 64, rope freq_base 10 000 000.
# Text-only (no mmproj).  Built-in chat template in the GGUF.
#
# Expert offload: --cpu-moe keeps all 256 expert weights in CPU RAM.
# Non-expert weights (~1.6 GB) fit entirely on the 24 GB card.
#
# KV cache: Q8_0 for both K and V.  With CTX_SIZE=200700 (66 900 per slot
# × 3 parallel) and 10 attention layers, the KV cache is ~2 GB — the
# requested 2 GB VRAM buffer.
#
# 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 file (UD-Q6_K_XL, 30 GB, text-only MoE hybrid).
MODEL_DIR=/home/dank/models/tiel-coder-35b
MODEL_FILE=Tiel-Coder-35B-A3B-UD-Q6_K_XL.gguf

# Upstream llama.cpp llama-server (CUDA build, latest master).
# Built with -DGGML_CUDA_FA_ALL_QUANTS=ON -DCMAKE_CUDA_ARCHITECTURES=86
# using the staged CUDA 13.2 toolkit at /home/dank/cuda13-stage.
LLAMA_SERVER=/home/dank/llama.cpp/build/bin/llama-server

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

# Total context budget across all parallel slots.  200700 / 3 = 66 900
# per slot.  The model's context_length is 262 144, so 66 900 is well
# within range.
CTX_SIZE=200700
PARALLEL=3

# Expert offload: all MoE expert weights pinned to CPU RAM.
CPU_MOE=1

# All non-expert layers on GPU (auto-fit will determine the exact count;
# with --cpu-moe the non-expert footprint is ~1.6 GB, leaving ample room).
N_GPU_LAYERS=999

# KV cache: Q8_0 for both K and V.  ~2 GB total for 200700 ctx × 3 slots
# × 10 attention layers × (2 KV heads × 256 dim × 1 byte) × 2 (K+V).
CACHE_TYPE_K=q8_0
CACHE_TYPE_V=q8_0

VERBOSITY=2

# Prefill batch sizing.
BATCH_SIZE=4096
UBATCH_SIZE=1024

# Sampling.
TEMPERATURE=1.0
TOP_K=20
TOP_P=0.95
MIN_P=0.0

# Compute threads lowered so other processes keep a core.
THREADS=7
THREADS_HTTP=8