# Tunables for frank-default-small (Ornith-1.5-35B-A3B CRACK Q6_K, MTP MoE,
# Dankserver, RTX 3090).
#
# Runtime: ik_llama.cpp llama-server (ikawrakow ik_llama.cpp, built
# 2026-08-26 from commit b166e269) on RTX 3090 24 GB; Ryzen 7 7700X; 62 GB
# RAM. Previous runtime was upstream llama.cpp b10121. MoE expert weights
# pinned to CPU with an explicit --override-tensor regex (not --n-cpu-moe).
# KV cache quantized to q8_0 with Hadamard transforms on both K and V.
# Split mode none (single GPU; graph would require 2+ devices).
#
# Build flags (IK_FA note, see docs/LLM/ikllama-ornith-dankserver.md) must
# ALWAYS include: -DGGML_CUDA_FA_ALL_QUANTS=ON and -DGGML_IQK_FA_ALL_QUANTS=ON
# so the quantized + Hadamard KV cache combos compile into the CUDA/CPU FA
# kernels. Replacing the HauhauCS Qwen3.6-35B-A3B model on 2026-08-24.
# Switched from CRACK Q8_0 to Q6_K on 2026-08-25.
#
# 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 (Q6_K 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-Q6_K.gguf
MMPROJ_FILE=mmproj-Ornith-1.5-35B-A3B-f16.gguf
# ik_llama.cpp llama-server (built 2026-08-26 from ikawrakow/ik_llama.cpp @
# b166e269; CUDA 13.2, -DGGML_CUDA_FA_ALL_QUANTS=ON -DGGML_IQK_FA_ALL_QUANTS=ON,
# arch 86 for the RTX 3090). Uses the staged pip cu13 toolkit at
# /home/dank/cuda13-stage. Rollback: switch to
# /home/dank/llama.cpp/build/bin/llama-server (upstream b10121).
LLAMA_SERVER=/home/dank/ik_llama.cpp/build/bin/llama-server

# Qwen-Sharp chat template from peculiar-ragdoll (tracked in the repo,
# staged on the host).
# Source: https://huggingface.co/peculiar-ragdoll/Qwen-Sharp-Chat-Templates
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 163840 ctx each (262144 lowered by 96k per stream for
# cache and checkpoint headroom) = 491520 total context pool. The per-slot
# 163840 is advertised in models.json.
CTX_SIZE=491520
PARALLEL=3

# Speculative decoding: ngram-mod only. MTP is intentionally disabled.
# ik_llama main uses canonical --spec-type ngram-mod:KEY=VAL form. Legacy
# --spec-ngram-mod-n-min/max/match are rejected. Mapping from the old config:
#   old --spec-ngram-mod-n-min  (48) -> n_min
#   old --spec-ngram-mod-n-max  (64) -> n_max
#   old --spec-ngram-mod-n-match (24 -> ngram lookup length) -> ngram_size_n
# SPEC_TYPE is passed through to --spec-type.
SPEC_TYPE=ngram-mod:n_min=48,n_max=64,ngram_size_n=24

# Expert offload via explicit tensor override (replaces --n-cpu-moe). The Q6_K
# layer audit found 630 MiB of expert tensors per block. Keep every
# full-attention block plus every block 35-40 on CUDA. The unique GPU set is
# 3,7,11,15,19,23,27,31,35,36,37,38,39,40. Move all other expert tensors to
# CPU. All non-expert tensors stay on the 24 GB card. Buffer type "CPU" is the
# CPU buft name on this host.
OVERRIDE_EXPERT='blk\.(0|1|2|4|5|6|8|9|10|12|13|14|16|17|18|20|21|22|24|25|26|28|29|30|32|33|34)\.ffn_(up|down|gate|gate_up)_(ch|)exps'
OVERRIDE_BUFT=CPU
# ik_llama --gpu-layers/-ngl does NOT accept the literal "all"; use 999 to
# mean "load as many layers as possible". Expert exps are pinned to CPU by
# OVERRIDE_EXPERT below.
N_GPU_LAYERS=999

# KV cache on GPU, both K and V at q8_0 plus Hadamard transforms on both
# caches to preserve quality at 8-bit. NOTE: ik_llama's fast q8_KV type
# crashes at model init on this MTP/multimodal arch with a ggml_view size
# assert (ggml.c:5427) at commit b166e269; plain q8_0 works. Docs recommend
# --k-cache-hadamard for quantized KV below Q6_0; we apply --v-cache-hadamard
# to V as well. Flash-attention is on by default.
CACHE_TYPE_K=q8_0
CACHE_TYPE_V=q8_0
K_CACHE_HADAMARD=1
V_CACHE_HADAMARD=1

# Split mode: none. Dankserver has a single RTX 3090 and ik_llama requires
# >= 2 devices for split-mode graph ('It is not possible to use split mode
# graph with less than 2 devices' is a hard load error). none is correct
# here and still works with OVERRIDE_EXPERT CPU expert offload.
SPLIT_MODE=none

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

# Prefill batch sizing. ubatch 1024 is selected for reduced compute-memory
# pressure and predictable latency under the ngram-mod deployment.
BATCH_SIZE=4096
UBATCH_SIZE=1024

# 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