# Tunables for frank-default-large (HauhauCS Qwen3.6-27B Q8_K_P, DFlash+ngram-mod, dankclaw)
# Runtime: llama.cpp llama-server; AMD Strix Halo (gfx1151) 96GB UMA; Ryzen AI MAX+ 395.
MODEL_DIR=/home/dank/models
ALIAS=frank-default-large
HOST=0.0.0.0
PORT=7770
# 3 parallel slots x 200700 ctx each = 602100 total context pool.
CTX_SIZE=602100
PARALLEL=3
# Spec: speculative decoding mode.
#   draft-dflash  - DFlash block-diffusion draft (benchmark winner pre-2026-08-14)
#                   BUT: premature EOS under parallel load when a new task
#                   reuses a cached prompt (shared draft ctx corruption). Retired.
#   draft-mtp     - MTP sidecar draft (a4lg/Qwen3.6-27B-MTP-ONLY-Q8_0.gguf)
#   ngram-mod     - draftless ngram matching (no draft model, no shared ctx)
# Benched 2026-08-14: see docs/frank-default-large-benchmark.md for the winner.
SPEC_TYPE=draft-mtp
# Draft model file (only used when SPEC_TYPE contains 'draft-').
# DFlash: Qwen3.6-27B-DFlash-Q8_0.gguf ; MTP: Qwen3.6-27B-MTP-ONLY-Q8_0.gguf
DRAFT_FILE=Qwen3.6-27B-MTP-ONLY-Q8_0.gguf
# Draft length per spec type: dflash 8, mtp 2-3.
SPEC_DRAFT_N_MAX=3
SPEC_NGRAM_MOD_N_MIN=48
SPEC_NGRAM_MOD_N_MAX=64
SPEC_NGRAM_MOD_N_MATCH=24
# Backend device from --list-devices. ROCm wins on generation; Vulkan renders
# DFlash spec unusable (NONE-op abort) and gen is slower on ngram (6.9 t/s).
DEVICE=ROCm0
# Dense model (Qwen3.6-27B, not MoE): no MoE CPU offload. Full offload.
N_GPU_LAYERS=all
# KV on GPU, quantized (K q8_0, V q8_0). V MUST match K: this llama.cpp
# build has GGML_CUDA_FA_ALL_QUANTS=OFF, and Flash Attention requires
# K type == V type. Mixed q8_0/f16 silently disables FA, collapsing
# long-context decode to ~1 t/s at 200k ctx. q8_0 V halves V memory too.
CACHE_TYPE_K=q8_0
CACHE_TYPE_V=q8_0
# Batch sizing: empirically verified 2026-08-13 with caches dropped.
# batch 8192 / ubatch 2048 loads and serves (61 GiB VRAM peak, ctx 602100).
# ubatch is the compute-graph driver; larger ubatch = more VRAM, faster prefill.
# Re-verified 2026-08-14 during the spec swap (see benchmark doc).
BATCH_SIZE=8192
UBATCH_SIZE=8192
# Sampling settings — per HauhauCS Qwen3.6-27B model card.
# Thinking-general: temp=1.0, top_p=0.95, top_k=20, min_p=0.
# Clients may override per-request; these are the server-side defaults.
# WARNING: do not name this variable TEMP. The ROCm HIP runtime reads the
# TEMP environment variable (JIT kernel-cache dir); TEMP=1.0 made the HIP
# runtime SEGV (NULL unref) during model load on Aug 13 2026.
TEMPERATURE=1.0
TOP_K=20
TOP_P=0.95
MIN_P=0.0
THREADS=12
THREADS_HTTP=1