Frank
e219fdf939
Total KV: ~12.8 GiB (6.4 GiB per slot × 2). Model is 98.5 GiB mmap'd into 116 GiB SVM-backed unified memory.
81 lines
3.3 KiB
Bash
81 lines
3.3 KiB
Bash
# Tunables for frank-default-large (kingjones777 Qwen3.8-Flash-Next
|
||
# ROCmFP4 STRIX_LEAN, qwen4exp hybrid MoE, Dankclaw, Strix Halo gfx1151).
|
||
#
|
||
# Runtime: ROCmFPX llama.cpp fork with PR #27742 (qwen4exp architecture)
|
||
# merged and built at /home/dank/GitPackages/ROCmFPX/build-qwen38.
|
||
# Build flags: -DGGML_HIP=ON -DGGML_HIP_ROCMI4_W4A4=ON
|
||
# -DCMAKE_HIP_ARCHITECTURES=gfx1151 -DGGML_CUDA_FA_ALL_QUANTS=ON
|
||
# -DLLAMA_BUILD_WEBUI=OFF -DCMAKE_EXE_LINKER_FLAGS=-no-pie.
|
||
# Replaced the kingjones Qwen3.8-27B Q6_0 AGENT deployment on 2026-09-01.
|
||
#
|
||
# Model: kingjones777/Qwen3.8-Flash-Next-ROCmFP4-STRIX_LEAN-GGUF.
|
||
# 56B MoE (512 experts, 10 used), 48 layers (12 attention + 36 SSM,
|
||
# full_attention_interval=4), 2 KV heads × 256 dim, embedding 2560,
|
||
# QSA indexer (4 heads, key_length 128, top_k 2048), hyper-connections
|
||
# (count=4, low_rank=320), PLE (layer 1, ngram_size=3, heads_per_ngram=8).
|
||
# Q4_0_ROCMFP4_STRIX_LEAN quant, 98.5 GiB, 3-part GGUF split.
|
||
# Text-only (no mmproj, no MTP draft head).
|
||
#
|
||
# Context: 262144 (256k) × 2 slots. f16 KV cache (~6.4 GiB per slot,
|
||
# ~12.8 GiB total). --fit off because the auto-fit code segfaults on this
|
||
# model's hyper-connection/indexer config; -ngl 999 places all layers on
|
||
# the SVM-backed GPU pool (116 GiB unified).
|
||
#
|
||
# 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.
|
||
|
||
# ROCmFPX llama-server (PR #27742 merged, build-qwen38).
|
||
LLAMA_BIN=/home/dank/GitPackages/ROCmFPX/build-qwen38/bin/llama-server
|
||
|
||
# Model files from
|
||
# https://huggingface.co/kingjones777/Qwen3.8-Flash-Next-ROCmFP4-STRIX_LEAN-GGUF
|
||
MODEL_DIR=/home/dank/models/kingjones-Qwen3.8-Flash-Next-ROCmFP4-STRIX_LEAN
|
||
MODEL_FILE=Qwen3.8-Flash-Next-ROCmFP4-STRIX_LEAN-00001-of-00003.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 thinking 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 (256k) × 2 slots. f16 KV, context checkpoints,
|
||
# prompt cache. The model is 98.5 GiB loaded via mmap into the Strix Halo
|
||
# unified memory pool (116 GiB SVM-backed). --fit off avoids the auto-fit
|
||
# segfault on this model's qwen4exp hyper-connection/indexer configuration.
|
||
CTX_SIZE=524288
|
||
PARALLEL=2
|
||
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
|
||
FIT=off
|
||
|
||
# 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.
|
||
HSA_OVERRIDE_GFX_VERSION=11.5.1
|
||
|
||
VERBOSITY=4 |