80 lines
2.9 KiB
Bash
80 lines
2.9 KiB
Bash
# Tunables for frank-default-large (charlie12345/ROCmFPX, dankclaw, Strix Halo
|
|
# gfx1151, ROCmI4 embedded MTP).
|
|
#
|
|
# Runtime: charlie12345/ROCmFPX commit c49ebdbd built with
|
|
# -DGGML_HIP_ROCMI4_W4A4=ON against the system ROCm (/opt/rocm-7.2.4, amdclang
|
|
# 22). Serves caf-eemin/Qwen3.8-27B-ROCmI4-MTP-GGUF (Q4_0_ROCMI4, embedded
|
|
# MTP, no separate draft head). Alias frank-default-large, port 7770.
|
|
#
|
|
# This model replaced kingjones777/Qwen3.8-27B-Uncensored-ROCmFP4-STRIX-MTP on
|
|
# 2026-08-25. The old kingjones ROCmFP4 GGUF + standalone MTP Q4_0 draft are
|
|
# retired on this slot.
|
|
|
|
# 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.
|
|
|
|
# charlie12345/ROCmFPX build with the ROCmI4 W4A4 path.
|
|
LLAMA_BIN=/home/dank/rocmi4-qwen38/ROCmFPX/build-rocmi4-w4a4/bin/llama-server
|
|
|
|
# Model files: embedded-MTP ROCmI4 GGUF + optional BF16 vision projector.
|
|
MODEL_DIR=/home/dank/models/eemin-Qwen3.8-27B-ROCMI4-MTP
|
|
MODEL_FILE=Qwen3.8-27B-Q4_0_ROCMI4.gguf
|
|
MMPROJ_FILE=mmproj-BF16.gguf
|
|
# 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=256
|
|
NUM_THREADS=16
|
|
THREAD_BATCH=32
|
|
CACHE_TYPE_K=f16
|
|
CACHE_TYPE_V=f16
|
|
CTX_CHECKPOINTS=16
|
|
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=16
|
|
MTP_N_MIN=0
|
|
MTP_P_MIN=0.60
|
|
SPEC_MTP_STRICT_QWEN=on
|
|
MTP_BACKEND_SAMPLING=on
|
|
SPEC_DRAFT_NGL=all
|
|
|
|
# Sampling (Sharp default).
|
|
TEMPERATURE=1.0
|
|
TOP_K=20
|
|
TOP_P=0.95
|
|
|
|
# Thinking on (Sharp template drives it; reasoning format projects the tar into
|
|
# reasoning_content).
|
|
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
|