77 lines
3.1 KiB
Bash
77 lines
3.1 KiB
Bash
# Tunables for frank-default-large (kingjones Qwen3.8 Uncensored Q6 AGENT,
|
|
# dankclaw, Strix Halo gfx1151).
|
|
#
|
|
# Runtime: ROCmFPX llama.cpp with TurboQuant support. Serves the kingjones
|
|
# AGENT GGUF plus its standalone MTP draft and vision projector. Alias
|
|
# frank-default-large, port 7770.
|
|
|
|
# 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).
|
|
# llama.cpp reads --host/--port/--temp as CLI flags, never as env vars.
|
|
|
|
# PromptForge ROCmFPX build and its historical ROCm 7.15 SDK environment.
|
|
LLAMA_BIN=/home/dank/ciru-qwen38/ROCmFPX/build-promptforge/bin/llama-server
|
|
ROCM_DEVEL=/home/dank/ling3-ciru/Ling-3.0-Flash-CIRU-int4-Strix-native/.venv/lib/python3.12/site-packages/_rocm_sdk_devel
|
|
ROCM_LIB=/home/dank/ling3-ciru/Ling-3.0-Flash-CIRU-int4-Strix-native/.venv/lib/python3.12/site-packages/_rocm_sdk_libraries
|
|
ROCM_CORE=/home/dank/ling3-ciru/Ling-3.0-Flash-CIRU-int4-Strix-native/.venv/lib/python3.12/site-packages/_rocm_sdk_core
|
|
|
|
# Model files from https://huggingface.co/kingjones777/Qwen3.8-27B-Uncensored-ROCmFP4-STRIX-MTP-GGUF.
|
|
MODEL_DIR=/home/dank/models/kingjones-Qwen3.8-27B-STRIX-MTP
|
|
MODEL_FILE=Qwen3.8-27B-Uncensored-Q6_0_ROCMFPX_AGENT.gguf
|
|
MTP_DRAFT_FILE=$MODEL_DIR/mtp-Qwen3.8-27B-Q4_0.gguf
|
|
MMPROJ_FILE=mmproj-Qwen3.8-27B-Q8_0.gguf
|
|
|
|
# Qwen-Sharp chat template (tracked in the repo, staged on the host). The Sharp
|
|
# template drives thinking on by default (medium effort); the server emits
|
|
# reasoning in DeepSeek format so clients receive reasoning_content separately
|
|
# instead of literal <think> tags in content.
|
|
CHAT_TEMPLATE_FILE=/home/dank/serverAppConfigs/scripts/chat-template.jinja
|
|
CHAT_TEMPLATE_KWARGS='{"enable_thinking":true,"preserve_thinking":true,"preserve_reasoning":true}'
|
|
|
|
# Alias + network.
|
|
ALIAS=frank-default-large
|
|
BIND_ADDR=0.0.0.0
|
|
LISTEN_PORT=7770
|
|
|
|
# Serving: 262144 context (the model's maximum), 1 slot. f16 KV, context
|
|
# checkpoints, prompt cache, standalone MTP draft on ROCm0. The full 262144
|
|
# context KV cache plus the ~28-30 GB Q8 model + MTP draft + mmproj fit in the
|
|
# lifted 114 GiB TTM/GTT budget on the Strix Halo (see the GTT 114 GiB change).
|
|
# Concurrent requests queue; the server never preempts a running generation.
|
|
CTX_SIZE=262144
|
|
PARALLEL=1
|
|
# Batch/ubatch follow the existing qualified Dankclaw profile.
|
|
BATCH_SIZE=4096
|
|
UBATCH_SIZE=4096
|
|
NUM_THREADS=16
|
|
THREAD_BATCH=32
|
|
CACHE_TYPE_K=f16
|
|
CACHE_TYPE_V=f16
|
|
CTX_CHECKPOINTS=16
|
|
CACHE_RAM=8192
|
|
|
|
# Standalone MTP draft head, loaded from MTP_DRAFT_FILE by the serve script.
|
|
MTP_N_MAX=4
|
|
MTP_N_MIN=0
|
|
MTP_P_MIN=0.0
|
|
MTP_P_SPLIT=0.10
|
|
|
|
# Sampling (Sharp default).
|
|
TEMPERATURE=0.7
|
|
TOP_K=20
|
|
TOP_P=0.8
|
|
MIN_P=0.0
|
|
PRESENCE_PENALTY=1.5
|
|
|
|
# Reasoning on (Sharp template drives it; preserve_thinking + preserve_reasoning
|
|
# keep the reasoning trail in the conversation). DeepSeek format projects the
|
|
# reasoning into the API's reasoning_content field instead of content tags.
|
|
REASONING=on
|
|
REASONING_FORMAT=deepseek
|
|
|
|
# Strix Halo unified memory + native gfx1151 detection for this ROCmFPX build.
|
|
HSA_OVERRIDE_GFX_VERSION=11.5.1
|
|
GGML_HIP_ENABLE_UNIFIED_MEMORY=1
|
|
|
|
VERBOSITY=4
|