Method run_all_quantizations

utils/quantize_embeddings.py:275–327

Run all quantizations Args: types_to_quantize: List of quantization types, tuples of (embedding_type, output_suffix)

(self, types_to_quantize)

            print(f"ℹ️  Keeping existing file: {model_file}")
    
    def run_all_quantizations(self, types_to_quantize):
        """
        Run all quantizations
        
        Args:
            types_to_quantize: List of quantization types, tuples of (embedding_type, output_suffix)
        """
        print(f"\n{'='*80}")
        print(f"🚀 Starting Embedding Quantization and Benchmarking")
        print(f"{'='*80}")
        print(f"📥 Input model: {self.input_model}")
        print(f"📤 Output directory: {self.output_dir}")
        print(f"📊 Stats directory: {self.stats_dir}")
        print(f"🔢 Total quantizations: {len(types_to_quantize)}")
        print(f"{'='*80}\n")
        
        total_start = datetime.now()
        
        for i, (embedding_type, output_suffix) in enumerate(types_to_quantize, 1):
            print(f"\n{'#'*80}")
            print(f"[{i}/{len(types_to_quantize)}] Processing {output_suffix} ({embedding_type})")
            print(f"{'#'*80}\n")
            
            # Quantize model
            success = self.quantize(embedding_type, output_suffix)
            
            if not success:
                print(f"⚠️  Skipping benchmark for {output_suffix} due to quantization failure")
                continue
            
            # Run benchmark
            bench_results = self.benchmark_model(output_suffix)
            
            if bench_results:
                self.results.append(bench_results)
            else:
                print(f"⚠️  Benchmark failed for {output_suffix}")
            
            # Cleanup model files (only delete newly created files)
            self.cleanup_model(output_suffix)
            
            print(f"\n{'#'*80}")
            print(f"✅ Completed {output_suffix}")
            print(f"{'#'*80}\n")
        
        total_end = datetime.now()
        total_duration = (total_end - total_start).total_seconds()
        
        # 保存结果到CSV
        self.save_results_to_csv()
        
        # 打印总结
        self.print_summary(total_duration)
    
    def save_results_to_csv(self):
        """将benchmark结果保存到CSV文件"""