#!/usr/bin/env bash set -euo pipefail server="${LLAMA_SERVER:-/path/to/rocmfp4-llama/build-strix-rocmfp4/bin/llama-server}" model="${MODEL:-CHADROCK3.6-27B-Coder-MTP-ROCmFP4-STRIX_LEAN.gguf}" mmproj="${MMPROJ:-mmproj-F32.mmproj}" exec env \ HSA_OVERRIDE_GFX_VERSION="${HSA_OVERRIDE_GFX_VERSION:-11.5.1}" \ GGML_HIP_ENABLE_UNIFIED_MEMORY="${GGML_HIP_ENABLE_UNIFIED_MEMORY:-1}" \ "$server" \ -m "$model" \ --mmproj "$mmproj" \ --alias chadrock3.6-27b-coder \ --host "${HOST:-127.0.0.1}" \ --port "${PORT:-8080}" \ --jinja \ -c "${CTX:-262144}" \ -ngl 999 \ -fa on \ -dev "${DEVICE:-ROCm0}" \ -b 512 \ -ub 512 \ -t 16 \ -tb 32 \ -ctk q8_0 \ -ctv q8_0 \ --ctx-checkpoints 0 \ --checkpoint-every-n-tokens -1 \ --spec-type draft-mtp \ --spec-draft-device "${SPEC_DRAFT_DEVICE:-ROCm0}" \ --spec-draft-ngl all \ --spec-draft-type-k q8_0 \ --spec-draft-type-v q8_0 \ --spec-draft-n-max 4 \ --spec-draft-n-min 0 \ --spec-draft-p-min 0.0 \ --spec-draft-p-split 0.10 \ --parallel 1 \ --metrics \ --no-mmap