mirror of
https://github.com/mudler/LocalAI.git
synced 2026-07-30 09:57:57 -04:00
bbe018c1a0
feat(bonsai): add PrismML llama.cpp fork backend + Bonsai gallery models Adds a new `bonsai` backend that runs the PrismML fork of llama.cpp (github.com/PrismML-Eng/llama.cpp, `prism` branch), which ships the Q1_0 (1-bit) and Q2_0 (ternary / 1.58-bit) weight-quantization kernels used by the Bonsai and Ternary-Bonsai models. Stock llama.cpp cannot decode these quants. Modeled on the turboquant backend: reuses backend/cpp/llama-cpp/grpc-server.cpp against the fork's libllama via a thin wrapper Makefile, so the sub-2-bit models are served with the same OpenAI-compatible API. No grpc-server allow-list patch is needed (bonsai adds weight quants, transparent to the server, not KV-cache types), and the reused server compiles cleanly against the fork with no skew patches (validated locally via a CPU docker build; patches/ is present but empty for any future re-pin skew). Backend wiring: backend/cpp/bonsai/, .docker/bonsai-compile.sh, backend/Dockerfile.bonsai, top-level Makefile targets, backend-matrix.yml build rows (CPU, CUDA 12/13, L4T, SYCL f32/f16, Vulkan, ROCm/hipblas), backend/index.yaml meta-backend + per-platform images, and a nightly bump_deps entry tracking the `prism` branch. Gallery: 8 entries across 4 families - bonsai-8b-1bit, ternary-bonsai-8b (+g64, +pq2), bonsai-27b-1bit (vision), ternary-bonsai-27b (+pq2, +g64, vision). The 27B models wire the mmproj vision tower; the DSpark speculative drafter GGUFs are not wired (custom semi-autoregressive drafter, not a standard llama.cpp draft model). Assisted-by: Claude:claude-opus-4-8 [Claude Code] Signed-off-by: Ettore Di Giacinto <mudler@localai.io> Co-authored-by: Ettore Di Giacinto <mudler@localai.io>
57 lines
1.8 KiB
Bash
Executable File
57 lines
1.8 KiB
Bash
Executable File
#!/bin/bash
|
|
set -ex
|
|
|
|
# Get the absolute current dir where the script is located
|
|
CURDIR=$(dirname "$(realpath "$0")")
|
|
|
|
cd /
|
|
|
|
echo "CPU info:"
|
|
grep -e "model\sname" /proc/cpuinfo | head -1
|
|
grep -e "flags" /proc/cpuinfo | head -1
|
|
|
|
BINARY=bonsai-fallback
|
|
|
|
# x86/arm64 ship a single bonsai-cpu-all built with ggml CPU_ALL_VARIANTS: ggml's
|
|
# backend registry dlopens the best libggml-cpu-*.so for this host, so no shell-side
|
|
# probing. ROCm ships only bonsai-fallback, so fall back to it when cpu-all is absent.
|
|
if [ -e "$CURDIR"/bonsai-cpu-all ]; then
|
|
BINARY=bonsai-cpu-all
|
|
fi
|
|
|
|
if [ -n "$LLAMACPP_GRPC_SERVERS" ]; then
|
|
if [ -e "$CURDIR"/bonsai-grpc ]; then
|
|
BINARY=bonsai-grpc
|
|
fi
|
|
fi
|
|
|
|
# Extend ld library path with the dir where this script is located/lib
|
|
if [ "$(uname)" == "Darwin" ]; then
|
|
export DYLD_LIBRARY_PATH="$CURDIR"/lib:$DYLD_LIBRARY_PATH
|
|
else
|
|
export LD_LIBRARY_PATH="$CURDIR"/lib:$LD_LIBRARY_PATH
|
|
# Tell rocBLAS where to find TensileLibrary data (GPU kernel tuning files)
|
|
if [ -d "$CURDIR/lib/rocblas/library" ]; then
|
|
export ROCBLAS_TENSILE_LIBPATH="$CURDIR"/lib/rocblas/library
|
|
fi
|
|
# Same for hipBLASLt (rocblaslt): the bundled libhipblaslt.so resolves its
|
|
# TensileLibrary_lazy_gfx*.dat kernel data relative to itself, so point it at
|
|
# the bundled data or it falls back to slow generic kernels (issue #10660).
|
|
if [ -d "$CURDIR/lib/hipblaslt/library" ]; then
|
|
export HIPBLASLT_TENSILE_LIBPATH="$CURDIR"/lib/hipblaslt/library
|
|
fi
|
|
fi
|
|
|
|
# If there is a lib/ld.so, use it
|
|
if [ -f "$CURDIR"/lib/ld.so ]; then
|
|
echo "Using lib/ld.so"
|
|
echo "Using binary: $BINARY"
|
|
exec "$CURDIR"/lib/ld.so "$CURDIR"/$BINARY "$@"
|
|
fi
|
|
|
|
echo "Using binary: $BINARY"
|
|
exec "$CURDIR"/$BINARY "$@"
|
|
|
|
# We should never reach this point, however just in case we do, run fallback
|
|
exec "$CURDIR"/bonsai-fallback "$@"
|