mirror of
https://github.com/mudler/LocalAI.git
synced 2026-07-30 09:57:57 -04:00
0a8a7fbbb4
Bump LLAMA_VERSION to 0d47ea7427463093e69128bf2c2f9cd06b3ee5b3 (73 commits touching common/, src/ and tools/server/). Two upstream changes break the backend: * ggml-org/llama.cpp#20834 folded common_params::use_mmap / use_mlock / use_direct_io into a single `load_mode` enum. LocalAI still exposes the three as independent settings (`mmap`, `mmlock`, and the `direct_io` option), so params_parse folds them once all three have been read, keeping the precedence the separate booleans had: direct I/O bypasses the page cache, mlock implies mmap, everything off is a plain buffered read. turboquant and bonsai compile this same grpc-server.cpp against forks that predate the refactor, so prepare.sh probes the checkout for LLAMA_LOAD_MODE_MMAP and generates llama_compat.h with LOCALAI_LEGACY_LOAD_MODE set accordingly. Probing beats a per-fork build flag here because the fork flavor targets disagree on whether they forward CMAKE_ARGS or EXTRA_CMAKE_ARGS, and it heals itself once a fork rebases past the refactor. * The MiniMax M3 patch no longer applies. Upstream merged the model half of llama.cpp#24523 (LLM_ARCH_MINIMAX_M3, src/models/minimax-m3.cpp, the gguf-py constants and conversion/minimax.py) but not the chat half, so the patch is re-cut to carry only the common/chat.cpp template detection and PEG parser, rebased onto the new pin and onto the thinking_end_tag -> thinking_end_tags rename. Dropping it wholesale (as #11008 did, reverted in #11136) would have silently regressed MiniMax M3 tool calling and thinking. Verified with a CPU docker build of the backend plus LoadModel and Predict against a real GGUF over gRPC in all four load modes. Assisted-by: Claude:claude-opus-5 [Claude Code] Signed-off-by: Ettore Di Giacinto <mudler@localai.io> Co-authored-by: Ettore Di Giacinto <mudler@localai.io>
62 lines
2.5 KiB
Bash
62 lines
2.5 KiB
Bash
#!/bin/bash
|
|
|
|
set -e
|
|
|
|
## Patches
|
|
|
|
## Apply patches from the `patches` directory. Runs under set -e so a
|
|
## rejected patch aborts the build here, loudly, instead of surfacing later
|
|
## as a confusing compile error. A missing or empty patches dir is a no-op.
|
|
if [ -d "patches" ]; then
|
|
for patch in $(ls patches); do
|
|
echo "Applying patch $patch"
|
|
patch -d llama.cpp/ -p1 < patches/$patch
|
|
done
|
|
fi
|
|
|
|
for file in $(ls llama.cpp/tools/server/); do
|
|
cp -rfv llama.cpp/tools/server/$file llama.cpp/tools/grpc-server/
|
|
done
|
|
|
|
cp -r CMakeLists.txt llama.cpp/tools/grpc-server/
|
|
cp -r grpc-server.cpp llama.cpp/tools/grpc-server/
|
|
# Shared message-reconstruction helpers (included by grpc-server.cpp) and their
|
|
# unit test (compiled only when -DLLAMA_GRPC_BUILD_TESTS=ON).
|
|
cp -r message_content.h llama.cpp/tools/grpc-server/
|
|
cp -r message_content_test.cpp llama.cpp/tools/grpc-server/
|
|
# Parent-death watcher (included by grpc-server.cpp) and its standalone unit
|
|
# test (run via backend/cpp/run-unit-tests.sh; also buildable under ctest).
|
|
cp -r parent_watch.h llama.cpp/tools/grpc-server/
|
|
cp -r parent_watch_test.cpp llama.cpp/tools/grpc-server/
|
|
cp -rfv llama.cpp/vendor/nlohmann/json.hpp llama.cpp/tools/grpc-server/
|
|
cp -rfv llama.cpp/vendor/cpp-httplib/httplib.h llama.cpp/tools/grpc-server/
|
|
|
|
## Fork-skew probe. Upstream folded common_params::use_mmap / use_mlock /
|
|
## use_direct_io into a single `load_mode` enum (ggml-org/llama.cpp#20834).
|
|
## turboquant and bonsai compile this very same grpc-server.cpp against forks
|
|
## that branched before that change, so the field set is decided from the
|
|
## checkout in front of us rather than from a per-fork build flag: the flavor
|
|
## targets disagree on whether they forward CMAKE_ARGS or EXTRA_CMAKE_ARGS, and
|
|
## probing heals itself the moment a fork rebases past the refactor.
|
|
if grep -q "LLAMA_LOAD_MODE_MMAP" llama.cpp/include/llama.h; then
|
|
echo "==> llama.cpp carries the load-mode enum, using common_params::load_mode"
|
|
LEGACY_LOAD_MODE=0
|
|
else
|
|
echo "==> llama.cpp predates the load-mode enum, using the legacy mmap/mlock/direct-io booleans"
|
|
LEGACY_LOAD_MODE=1
|
|
fi
|
|
cat > llama.cpp/tools/grpc-server/llama_compat.h <<EOF
|
|
// Generated by backend/cpp/llama-cpp/prepare.sh. Do not edit.
|
|
#pragma once
|
|
#define LOCALAI_LEGACY_LOAD_MODE ${LEGACY_LOAD_MODE}
|
|
EOF
|
|
|
|
set +e
|
|
if grep -q "grpc-server" llama.cpp/tools/CMakeLists.txt; then
|
|
echo "grpc-server already added"
|
|
else
|
|
echo "add_subdirectory(grpc-server)" >> llama.cpp/tools/CMakeLists.txt
|
|
fi
|
|
set -e
|
|
|