feat(quantization): add quantization backend (#9096)

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

backend/python/llama-cpp-quantization/Makefile

@@ -0,0 +1,26 @@
+# Version of llama.cpp to fetch convert_hf_to_gguf.py from
+LLAMA_CPP_CONVERT_VERSION ?= master
+
+.PHONY: llama-cpp-quantization
+llama-cpp-quantization:
+	LLAMA_CPP_CONVERT_VERSION=$(LLAMA_CPP_CONVERT_VERSION) bash install.sh
+
+.PHONY: run
+run: llama-cpp-quantization
+	@echo "Running llama-cpp-quantization..."
+	bash run.sh
+	@echo "llama-cpp-quantization run."
+
+.PHONY: test
+test: llama-cpp-quantization
+	@echo "Testing llama-cpp-quantization..."
+	bash test.sh
+	@echo "llama-cpp-quantization tested."
+
+.PHONY: protogen-clean
+protogen-clean:
+	$(RM) backend_pb2_grpc.py backend_pb2.py
+
+.PHONY: clean
+clean: protogen-clean
+	rm -rf venv __pycache__