mirror of
https://github.com/mudler/LocalAI.git
synced 2026-06-01 04:28:59 -04:00
cd6079b2f3
spiritbuun/buun-llama-cpp is a fork of TheTom/llama-cpp-turboquant that adds two independent features on top: DFlash block-diffusion speculative decoding (via a dedicated DFlashDraftModel GGUF arch) and two extra TCQ KV-cache variants (turbo2_tcq, turbo3_tcq) on top of TurboQuant's turbo2/turbo3/turbo4. Follows the turboquant thin-wrapper pattern — reuses backend/cpp/llama-cpp grpc-server sources verbatim, patches only the build copy to extend the KV allow-list and wire up buun-exclusive tree_budget / draft_topk options. DraftModel is already wired end-to-end (proto field 39 → params.speculative), so DFlash activation only needs the existing options passthrough (spec_type:dflash) plus the drafter path in draft_model. CacheTypeOptions now surfaces the five turbo* values so the React UI dropdown shows them — benefits turboquant too (previously users had to type them in YAML manually). Assisted-by: Claude:Opus-4.7 [Read] [Edit] [Bash] [WebFetch] Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
58 lines
2.5 KiB
Bash
Executable File
58 lines
2.5 KiB
Bash
Executable File
#!/bin/bash
|
|
|
|
# Script to copy the appropriate libraries based on architecture
|
|
# This script is used in the final stage of the Dockerfile
|
|
|
|
set -e
|
|
|
|
CURDIR=$(dirname "$(realpath $0)")
|
|
REPO_ROOT="${CURDIR}/../../.."
|
|
|
|
# Create lib directory
|
|
mkdir -p $CURDIR/package/lib
|
|
|
|
cp -avrf $CURDIR/buun-llama-cpp-* $CURDIR/package/
|
|
cp -rfv $CURDIR/run.sh $CURDIR/package/
|
|
|
|
# Detect architecture and copy appropriate libraries
|
|
if [ -f "/lib64/ld-linux-x86-64.so.2" ]; then
|
|
# x86_64 architecture
|
|
echo "Detected x86_64 architecture, copying x86_64 libraries..."
|
|
cp -arfLv /lib64/ld-linux-x86-64.so.2 $CURDIR/package/lib/ld.so
|
|
cp -arfLv /lib/x86_64-linux-gnu/libc.so.6 $CURDIR/package/lib/libc.so.6
|
|
cp -arfLv /lib/x86_64-linux-gnu/libgcc_s.so.1 $CURDIR/package/lib/libgcc_s.so.1
|
|
cp -arfLv /lib/x86_64-linux-gnu/libstdc++.so.6 $CURDIR/package/lib/libstdc++.so.6
|
|
cp -arfLv /lib/x86_64-linux-gnu/libm.so.6 $CURDIR/package/lib/libm.so.6
|
|
cp -arfLv /lib/x86_64-linux-gnu/libgomp.so.1 $CURDIR/package/lib/libgomp.so.1
|
|
cp -arfLv /lib/x86_64-linux-gnu/libdl.so.2 $CURDIR/package/lib/libdl.so.2
|
|
cp -arfLv /lib/x86_64-linux-gnu/librt.so.1 $CURDIR/package/lib/librt.so.1
|
|
cp -arfLv /lib/x86_64-linux-gnu/libpthread.so.0 $CURDIR/package/lib/libpthread.so.0
|
|
elif [ -f "/lib/ld-linux-aarch64.so.1" ]; then
|
|
# ARM64 architecture
|
|
echo "Detected ARM64 architecture, copying ARM64 libraries..."
|
|
cp -arfLv /lib/ld-linux-aarch64.so.1 $CURDIR/package/lib/ld.so
|
|
cp -arfLv /lib/aarch64-linux-gnu/libc.so.6 $CURDIR/package/lib/libc.so.6
|
|
cp -arfLv /lib/aarch64-linux-gnu/libgcc_s.so.1 $CURDIR/package/lib/libgcc_s.so.1
|
|
cp -arfLv /lib/aarch64-linux-gnu/libstdc++.so.6 $CURDIR/package/lib/libstdc++.so.6
|
|
cp -arfLv /lib/aarch64-linux-gnu/libm.so.6 $CURDIR/package/lib/libm.so.6
|
|
cp -arfLv /lib/aarch64-linux-gnu/libgomp.so.1 $CURDIR/package/lib/libgomp.so.1
|
|
cp -arfLv /lib/aarch64-linux-gnu/libdl.so.2 $CURDIR/package/lib/libdl.so.2
|
|
cp -arfLv /lib/aarch64-linux-gnu/librt.so.1 $CURDIR/package/lib/librt.so.1
|
|
cp -arfLv /lib/aarch64-linux-gnu/libpthread.so.0 $CURDIR/package/lib/libpthread.so.0
|
|
else
|
|
echo "Error: Could not detect architecture"
|
|
exit 1
|
|
fi
|
|
|
|
# Package GPU libraries based on BUILD_TYPE
|
|
GPU_LIB_SCRIPT="${REPO_ROOT}/scripts/build/package-gpu-libs.sh"
|
|
if [ -f "$GPU_LIB_SCRIPT" ]; then
|
|
echo "Packaging GPU libraries for BUILD_TYPE=${BUILD_TYPE:-cpu}..."
|
|
source "$GPU_LIB_SCRIPT" "$CURDIR/package/lib"
|
|
package_gpu_libs
|
|
fi
|
|
|
|
echo "Packaging completed successfully"
|
|
ls -liah $CURDIR/package/
|
|
ls -liah $CURDIR/package/lib/
|