# Tunables for frank-default-small (Ornith-1.5-35B-A3B CRACK Q8_0, MTP MoE,
# Dankserver, RTX 3090).
#
# Runtime: upstream llama.cpp llama-server (b10121). RTX 3090 24 GB; Ryzen
# 7 7700X; 62 GB RAM. MoE expert weights pinned to CPU with an explicit
# --override-tensor regex (not --n-cpu-moe). Replaced the HauhauCS
# Qwen3.6-35B-A3B model on 2026-08-24.
#
# 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 files (Q8_0 CRACK GGUF + f16 mmproj vision encoder + MTP head bundled
# in the GGUF). Dealign2026-08-24.
MODEL_DIR=/home/dank/models/Ornith-1.5-35B-A3B-CRACK
MODEL_FILE=Ornith-1.5-35B-A3B-CRACK-Q8_0.gguf
MMPROJ_FILE=mmproj-Ornith-1.5-35B-A3B-f16.gguf
# Upstream llama.cpp binary (b10121).
LLAMA_SERVER=/home/dank/llama.cpp/build/bin/llama-server

# Qwen-Sharp chat template (tracked in the repo, staged on the host).
CHAT_TEMPLATE_FILE=/home/dank/serverAppConfigs/scripts/chat-template.jinja

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

# 3 parallel slots x 229376 ctx each (262144 lowered by 32k per stream for
# cache headroom) = 688128 total context pool. The per-slot 229376 matches
# the per-slot context advertised in models.json (229376).
CTX_SIZE=688128
PARALLEL=3

# Spec: MoE model with a bundled MTP head -> native draft-mtp, n_max 4
# (the knee). ngram under MTP hurts; MTP alone is the proven best for MoE.
SPEC_TYPE=draft-mtp
SPEC_DRAFT_N_MAX=4
SPEC_DRAFT_N_MIN=0
SPEC_DRAFT_P_MIN=0.0

# Expert offload via explicit tensor override (replaces --n-cpu-moe). Only
# the MoE FFN exps tensors move to CPU; everything else up to --gpu-layers
# stays on the 24 GB card. The regex is the same one the built-in --cpu-moe
# expands. Buffer type "CPU" is the CPU buft name on this host.
OVERRIDE_EXPERT='\.ffn_(up|down|gate|gate_up)_(ch|)exps'
OVERRIDE_BUFT=CPU
N_GPU_LAYERS=all

# KV cache on GPU, both K and V at f16.
CACHE_TYPE_K=f16
CACHE_TYPE_V=f16

VERBOSITY=4
# Store context checkpoints in RAM to hold peak GPU memory down.
CTX_CHECKPOINTS=16

# Big prefill batches.
BATCH_SIZE=4096
UBATCH_SIZE=2048

# Eager RAM load (expert weights on CPU; ~31 GB RAM).
NO_MMAP=1

# Sampling (Dealign Ornith model card, thinking-general).
TEMPERATURE=1.0
TOP_K=20
TOP_P=0.95
MIN_P=0.0

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