60 lines
2.1 KiB
Bash
60 lines
2.1 KiB
Bash
# Tunables for frank-default-large (upstream llama.cpp PR #27342 DFlash2,
|
|
# Vulkan backend, dankclaw, Strix Halo gfx1151).
|
|
#
|
|
# Runtime: llama.cpp PR #27342 built with GGML_VULKAN=ON serving
|
|
# unsloth/Qwen3.8-27B-UD-Q8_K_XL (target) with a z-lab DFlash2 drafter
|
|
# (Qwen3.8-27B-DFlash2-Q4_K_M). Target at 31.4 GB, DFlash2 drafter at 2.0 GB.
|
|
# Alias frank-default-large, port 52625.
|
|
#
|
|
# DFlash2 runs on the Vulkan (RADV) backend. Its candidate selector needs
|
|
# TOP_K + ARGMAX, which the HIP backend does not implement. This replaced
|
|
# the CIRU HIP runtime on 2026-08-21. See docs/dflash2-large-vulkan.md.
|
|
#
|
|
# 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 deployment uses Vulkan, not HIP, but the rule stays for
|
|
# portability.
|
|
|
|
# Upstream llama.cpp DFlash2 binary (PR #27342, Vulkan build).
|
|
LLAMA_BIN=/home/dank/llama.cpp-dflash2/build-dflash2/bin/llama-server
|
|
|
|
# Model files. The target (UD-Q8_K_XL) was already on disk; the DFlash2
|
|
# drafter was added for this deployment. Both live in /home/dank/models.
|
|
MODEL_DIR=/home/dank/models
|
|
MODEL_FILE=Qwen3.8-27B-UD-Q8_K_XL.gguf
|
|
DRAFT_FILE=Qwen3.8-27B-DFlash2-Q4_K_M.gguf
|
|
|
|
ALIAS=frank-default-large
|
|
BIND_ADDR=0.0.0.0
|
|
LISTEN_PORT=52625
|
|
|
|
# Serving: full native 262144 context, 1 slot. The Vulkan device reports
|
|
# 113942 MiB; KV at 262144 x 64 KiB/cell is ~16 GiB. rocm-smi reports the
|
|
# 64 GiB budget; trust the runtime for the addressable SVM pool.
|
|
CTX_SIZE=262144
|
|
PARALLEL=1
|
|
BATCH_SIZE=4096
|
|
UBATCH_SIZE=4096
|
|
CACHE_TYPE_K=f16
|
|
CACHE_TYPE_V=f16
|
|
CTX_CHECKPOINTS=16
|
|
CACHE_RAM=8192
|
|
|
|
# DFlash2 speculative decoding. The drafter's trained block size is 8;
|
|
# SPEC_DRAFT_N_MAX clamps to it. TOP_K selector (top 16 candidates).
|
|
SPEC_TYPE=draft-dflash
|
|
SPEC_DRAFT_N_MAX=8
|
|
SPEC_DRAFT_N_MIN=0
|
|
SPEC_DRAFT_P_MIN=0.0
|
|
SPEC_DRAFT_P_SPLIT=0.10
|
|
|
|
# Sampling (model card defaults, thinking-general).
|
|
TEMPERATURE=0.7
|
|
TOP_P=0.95
|
|
|
|
# Thinking enabled. deepseek format moves the thinking reasoning into
|
|
# message.reasoning_content (OpenAI-compatible).
|
|
REASONING=on
|
|
REASONING_FORMAT=deepseek
|
|
|
|
VERBOSITY=4 |