Add llama.cpp LLM inference engine

ok sthen@

misc/llama.cpp/Makefile

@@ -0,0 +1,28 @@
+COMMENT =		LLM inference system
+
+GH_ACCOUNT =		ggerganov
+GH_PROJECT =		llama.cpp
+GH_TAGNAME =		b4589
+PKGNAME =		llama-cpp-0.0.${GH_TAGNAME:S/b//}
+
+SHARED_LIBS +=		ggml-base 0.0
+SHARED_LIBS +=		ggml-cpu 0.0
+SHARED_LIBS +=		ggml 0.0
+SHARED_LIBS +=		llama 0.0
+SHARED_LIBS +=		llava_shared 0.0
+
+CATEGORIES =		misc
+
+HOMEPAGE =		https://github.com/ggerganov/llama.cpp
+
+# MIT
+PERMIT_PACKAGE =	Yes
+
+WANTLIB +=		m pthread ${COMPILER_LIBCXX}
+
+MODULES =		devel/cmake
+
+CONFIGURE_ARGS =	-DGGML_CCACHE=Off \
+			-DGGML_NATIVE=Off
+
+.include <bsd.port.mk>

misc/llama.cpp/distinfo

@@ -0,0 +1,2 @@
+SHA256 (llama.cpp-b4589.tar.gz) = EUv6v5gdpBydZSAZ7t5eY1v7J8PBG9VeLCO8jfZ8qZM=
+SIZE (llama.cpp-b4589.tar.gz) = 20518474

misc/llama.cpp/pkg/DESCR

@@ -0,0 +1,3 @@
+Inference of Meta's LLaMA model (and others) in pure C/C++ with
+minimal setup and state-of-the-art performance on a wide range
+of hardware

misc/llama.cpp/pkg/PLIST

@@ -0,0 +1,89 @@
+bin/convert_hf_to_gguf.py
+@bin bin/llama-batched
+@bin bin/llama-batched-bench
+@bin bin/llama-bench
+@bin bin/llama-cli
+@bin bin/llama-convert-llama2c-to-ggml
+@bin bin/llama-cvector-generator
+@bin bin/llama-embedding
+@bin bin/llama-eval-callback
+@bin bin/llama-export-lora
+@bin bin/llama-gbnf-validator
+@bin bin/llama-gen-docs
+@bin bin/llama-gguf
+@bin bin/llama-gguf-hash
+@bin bin/llama-gguf-split
+@bin bin/llama-gritlm
+@bin bin/llama-imatrix
+@bin bin/llama-infill
+@bin bin/llama-llava-cli
+@bin bin/llama-lookahead
+@bin bin/llama-lookup
+@bin bin/llama-lookup-create
+@bin bin/llama-lookup-merge
+@bin bin/llama-lookup-stats
+@bin bin/llama-minicpmv-cli
+@bin bin/llama-parallel
+@bin bin/llama-passkey
+@bin bin/llama-perplexity
+@bin bin/llama-quantize
+@bin bin/llama-quantize-stats
+@bin bin/llama-qwen2vl-cli
+@bin bin/llama-retrieval
+@bin bin/llama-run
+@bin bin/llama-save-load-state
+@bin bin/llama-server
+@bin bin/llama-simple
+@bin bin/llama-simple-chat
+@bin bin/llama-speculative
+@bin bin/llama-speculative-simple
+@bin bin/llama-tokenize
+@bin bin/llama-tts
+@bin bin/test-arg-parser
+@bin bin/test-autorelease
+@bin bin/test-backend-ops
+@bin bin/test-barrier
+@bin bin/test-chat-template
+@bin bin/test-gguf
+@bin bin/test-grammar-integration
+@bin bin/test-grammar-parser
+@bin bin/test-json-schema-to-grammar
+@bin bin/test-llama-grammar
+@bin bin/test-log
+@bin bin/test-model-load-cancel
+@bin bin/test-quantize-fns
+@bin bin/test-quantize-perf
+@bin bin/test-rope
+@bin bin/test-sampling
+@bin bin/test-tokenizer-0
+@bin bin/test-tokenizer-1-bpe
+@bin bin/test-tokenizer-1-spm
+include/ggml-alloc.h
+include/ggml-backend.h
+include/ggml-blas.h
+include/ggml-cann.h
+include/ggml-cpu.h
+include/ggml-cuda.h
+include/ggml-kompute.h
+include/ggml-metal.h
+include/ggml-opt.h
+include/ggml-rpc.h
+include/ggml-sycl.h
+include/ggml-vulkan.h
+include/ggml.h
+include/gguf.h
+include/llama-cpp.h
+include/llama.h
+lib/cmake/
+lib/cmake/ggml/
+lib/cmake/ggml/ggml-config.cmake
+lib/cmake/ggml/ggml-version.cmake
+lib/cmake/llama/
+lib/cmake/llama/llama-config.cmake
+lib/cmake/llama/llama-version.cmake
+@lib lib/libggml-base.so.${LIBggml-base_VERSION}
+@lib lib/libggml-cpu.so.${LIBggml-cpu_VERSION}
+@lib lib/libggml.so.${LIBggml_VERSION}
+@lib lib/libllama.so.${LIBllama_VERSION}
+@lib lib/libllava_shared.so.${LIBllava_shared_VERSION}
+lib/pkgconfig/llama.pc