llm_perf/benchmark_runners/cpu/update_llm_perf_cpu_pytorch.py [72:107]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
            no_weights=True,
            library="transformers",
            task="text-generation",
            torch_dtype=torch_dtype,
            quantization_scheme=quant_scheme,
            quantization_config=quant_config,
            attn_implementation=attn_implementation,
            model_kwargs={"trust_remote_code": True},
        )

        return BenchmarkConfig(
            name=f"{weights_config}-{attn_implementation}",
            scenario=scenario_config,
            launcher=launcher_config,
            backend=backend_config,
        )

    def _get_weights_configs(self, subset) -> Dict[str, Dict[str, Any]]:
        if subset == "unquantized":
            return {
                "float32": {
                    "torch_dtype": "float32",
                    "quant_scheme": None,
                    "quant_config": {},
                },
                "float16": {
                    "torch_dtype": "float16",
                    "quant_scheme": None,
                    "quant_config": {},
                },
                "bfloat16": {
                    "torch_dtype": "bfloat16",
                    "quant_scheme": None,
                    "quant_config": {},
                },
            }
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



llm_perf/benchmark_runners/cuda/update_llm_perf_cuda_pytorch.py [83:118]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
            no_weights=True,
            library="transformers",
            task="text-generation",
            torch_dtype=torch_dtype,
            quantization_scheme=quant_scheme,
            quantization_config=quant_config,
            attn_implementation=attn_implementation,
            model_kwargs={"trust_remote_code": True},
        )

        return BenchmarkConfig(
            name=f"{weights_config}-{attn_implementation}",
            scenario=scenario_config,
            launcher=launcher_config,
            backend=backend_config,
        )

    def _get_weights_configs(self, subset) -> Dict[str, Dict[str, Any]]:
        if subset == "unquantized":
            return {
                "float32": {
                    "torch_dtype": "float32",
                    "quant_scheme": None,
                    "quant_config": {},
                },
                "float16": {
                    "torch_dtype": "float16",
                    "quant_scheme": None,
                    "quant_config": {},
                },
                "bfloat16": {
                    "torch_dtype": "bfloat16",
                    "quant_scheme": None,
                    "quant_config": {},
                },
            }
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -