llm-inference 4 retrieval 2 large-language-models 1 post-training static quantization 1 post-training dynamic quantization 1 quantization-aware training 1 tuning strategy 1 4-bits 1 autoround 1 chatbot 1 chatpdf 1 gaudi3 1 habana 1 intel-optimized-llamacpp 1 large-language-model 1 llm-cpu 1 neural-chat 1 neural-chat-7b 1 rag 1 streamingllm 1 deepseek 1 inference 1 llm-serving 1 llms 1 qwen 1 transformer 1 api-rest 1 cuda 1 inference-engine 1 inferentia 1 intel 1 lora 1 machine-learning 1 rocm 1 tpu 1 quantization 1 auto-tuning 1