# Tunables for the Ling-3.0-flash TRAIL on dankclaw (frank-dragoon-ling).
# This REPLACES frank-default-large (Qwen3.6-27B) temporarily. To switch
# back: systemctl stop frank-dragoon-ling && systemctl start frank-default-large.
# Runtime: llama.cpp FORK bailingmoe3-support; Vulkan + AMD GTT.
#
# Memory model (amdgpu Strix Halo gfx1151, 8x16GB LPDDR5 = 128 GiB physical):
#   - firmware UMA carve-out gives the iGPU ~96 GiB VRAM (rocm-smi "VRAM total").
#   - CPU system RAM is the remainder (~30 GiB; kernel MemTotal).
#   - Vulkan (RADV) reports an ~111.2 GiB heap (113910 MiB) - larger than ROCm's
#     96 GiB, because Vulkan can also reach system memory via GTT.
#   - Q6_K is 98.26 GiB, leaving only ~13 GiB of heap for KV + graphs, so keep
#     the context small (Ling uses MLA/KDA, so KV stays small). Tune CTX_SIZE.
MODEL_DIR=/home/dank/models
MODEL_FILE=Ling-3.0-flash-Q6_K.gguf
ALIAS=frank-default-large   # keep the API alias so clients are unaffected
HOST=0.0.0.0
PORT=7770
# Context: Q6_K uses ~98.7 GiB of the ~111.2 GiB Vulkan heap; Ling's MLA/KDA
# KV is tiny (~2.5 GiB for 256k), so a large context fits. 262144 total = 2
# slots x 131072, ~10 GiB heap headroom after load. Verified 2026-08-14.
CTX_SIZE=262144
PARALLEL=2
# MTP is bundled in the Ling GGUF itself (block 42) - no separate draft file.
# Layering ngram-mod under MTP (draft-mtp,ngram-mod) re-drafts via ngram.
SPEC_TYPE=none
SPEC_DRAFT_N_MAX=3
SPEC_NGRAM_MOD_N_MIN=48
SPEC_NGRAM_MOD_N_MAX=64
SPEC_NGRAM_MOD_N_MATCH=24
# Vulkan exposes the larger heap (UMA + GTT) vs ROCm. Use Vulkan0.
DEVICE=Vulkan0
N_GPU_LAYERS=all
FLASH_ATTN=auto
# Batch kept small-leaning for the tight memory budget; tune with CTX_SIZE.
BATCH_SIZE=3072
UBATCH_SIZE=3072

# Diagnostics: high verbosity + a dedicated log file for investigating the
# premature 'stop' reports. -lv 4 = verbose (ggml); 5 = debug.
VERBOSITY=0
# Sampling defaults (model card: reasoning-capable; leave temp/top to default)
TEMPERATURE=1.0
TOP_K=20
TOP_P=0.95
MIN_P=0.0
THREADS=12
THREADS_HTTP=1