81 lines
2.9 KiB
Bash
81 lines
2.9 KiB
Bash
# Tunables for frank-default-large (CIRU/Kairic Edge ROCmFPX v1.2, dankclaw,
|
|
# Strix Halo gfx1151).
|
|
#
|
|
# Runtime: ciru-ai/ROCmFPX tag kairic-edge-qwen38-27b-v1.2, commit
|
|
# 205a3e5f40e5542e2f2eb68e3d3f81f918b1d895, built with the pinned gfx1151
|
|
# Prompt Forge / IU4 settings against /opt/rocm. Serves the Kairic Edge
|
|
# authoritative GGUF plus three required .pfs sidecars. 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.
|
|
|
|
# ciru-ai/ROCmFPX Kairic Edge v1.2 build.
|
|
LLAMA_BIN=/home/dank/ciru-qwen38/ROCmFPX/build-kairic/bin/llama-server
|
|
|
|
# Model files: authoritative GGUF plus all required Kairic Edge sidecars.
|
|
MODEL_DIR=/home/dank/models/Kairic-Qwen3.8-27B-IU4-Edge
|
|
MODEL_FILE=Qwen3.8-27B-IU4-Kairic-Edge.gguf
|
|
KAIRIC_FFN_SIDECAR=$MODEL_DIR/Qwen3.8-27B-Kairic-IU4-FFN.pfs
|
|
KAIRIC_GDN_SIDECAR=$MODEL_DIR/Qwen3.8-27B-Kairic-IU4-GDN.pfs
|
|
KAIRIC_GDN_OUTPUT_SIDECAR=$MODEL_DIR/Qwen3.8-27B-Kairic-IU4-GDN-Output.pfs
|
|
KAIRIC_EDGE_COMPATIBILITY_MODE=1
|
|
# No separate MTP draft head: the MTP/NextN head is embedded in the main GGUF,
|
|
# so no --model-draft is passed. Kept for scripts that reference the var.
|
|
MTP_DRAFT_FILE=
|
|
|
|
# Qwen-Sharp chat template (tracked in the repo, staged on the host). The Sharp
|
|
# template drives thinking on by default (medium effort) and produces the
|
|
# peg-native + deepseek chat/reasoning shape the Pi agent expects.
|
|
CHAT_TEMPLATE_FILE=/home/dank/serverAppConfigs/scripts/chat-template.jinja
|
|
CHAT_TEMPLATE_KWARGS='{"enable_thinking":true,"preserve_thinking":true}'
|
|
|
|
# Alias + network.
|
|
ALIAS=frank-default-large
|
|
BIND_ADDR=0.0.0.0
|
|
LISTEN_PORT=7770
|
|
|
|
# Serving: 65536 context (192K below the model's 262144 maximum), 1 slot. f16
|
|
# KV, context checkpoints, prompt cache, strict-MTP embedded draft on ROCm0.
|
|
# This leaves sufficient unified-memory headroom for the model plus KV cache.
|
|
# Concurrent requests queue; the server never preempts a running generation.
|
|
CTX_SIZE=65536
|
|
PARALLEL=1
|
|
# Batch/ubatch follow the qualified ROCmI4 W4A4 profile (see the bench in
|
|
# scripts/bench-ubatch-rocmi4.sh for the ubatch sweep on 8k contexts).
|
|
BATCH_SIZE=512
|
|
UBATCH_SIZE=512
|
|
NUM_THREADS=16
|
|
THREAD_BATCH=32
|
|
CACHE_TYPE_K=f16
|
|
CACHE_TYPE_V=f16
|
|
CTX_CHECKPOINTS=32
|
|
CACHE_RAM=8192
|
|
|
|
# Embedded-MTP (qwen35 NextN) qualified profile. The head is in the main GGUF,
|
|
# so the draft runs with all layers on ROCm0 (no --model-draft).
|
|
MTP_N_MAX=4
|
|
MTP_N_MIN=0
|
|
MTP_P_MIN=0.0
|
|
MTP_P_SPLIT=0.10
|
|
KAIRIC_EDGE_COMPATIBILITY_MODE=1
|
|
|
|
# Sampling (Sharp default).
|
|
TEMPERATURE=0.7
|
|
TOP_K=20
|
|
TOP_P=0.8
|
|
MIN_P=0.0
|
|
PRESENCE_PENALTY=1.5
|
|
|
|
# Thinking on (Sharp template drives it; reasoning format projects the tar into
|
|
# reasoning_content).
|
|
REASONING=off
|
|
REASONING_FORMAT=none
|
|
|
|
# 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
|