path	# lines of code
pyproject.toml	60
optimum/quanto/models/__init__.py	12
optimum/quanto/models/transformers_models.py	105
optimum/quanto/models/shared_dict.py	24
optimum/quanto/models/diffusers_models.py	109
optimum/quanto/__init__.py	7
optimum/quanto/quantize.py	91
optimum/quanto/calibrate.py	102
optimum/quanto/subpackage/__init__.py	1
optimum/quanto/subpackage/commands/base.py	14
optimum/quanto/subpackage/commands/__init__.py	1
optimum/quanto/subpackage/commands/quantize.py	101
optimum/quanto/library/unpack.py	14
optimum/quanto/library/__init__.py	4
optimum/quanto/library/quantize.py	50
optimum/quanto/library/extensions/cuda/__init__.py	152
optimum/quanto/library/extensions/cuda/marlin/gptq_marlin_repack.cuh	9
optimum/quanto/library/extensions/cuda/marlin/marlin_cuda_kernel.cu	776
optimum/quanto/library/extensions/cuda/marlin/fp8_marlin.cuh	14
optimum/quanto/library/extensions/cuda/marlin/gptq_marlin_dtypes.cuh	60
optimum/quanto/library/extensions/cuda/marlin/gptq_marlin_repack.cu	271
optimum/quanto/library/extensions/cuda/marlin/marlin_cuda.cpp	56
optimum/quanto/library/extensions/cuda/marlin/fp8_marlin.cu	1150
optimum/quanto/library/extensions/cuda/marlin/marlin_cuda.h	13
optimum/quanto/library/extensions/cuda/marlin/gptq_marlin.cuh	59
optimum/quanto/library/extensions/cuda/marlin/marlin_cuda_kernel.cuh	34
optimum/quanto/library/extensions/cuda/unpack.cu	77
optimum/quanto/library/extensions/cuda/unpack.h	2
optimum/quanto/library/extensions/cuda/awq/v2/gemm_cuda.h	2
optimum/quanto/library/extensions/cuda/awq/v2/gemv_cuda.cu	280
optimum/quanto/library/extensions/cuda/awq/v2/gemv_cuda.h	11
optimum/quanto/library/extensions/cuda/awq/v2/gemm_cuda.cu	968
optimum/quanto/library/extensions/cuda/awq/v2/semaphore.h	49
optimum/quanto/library/extensions/cuda/awq/dequantize.cuh	67
optimum/quanto/library/extensions/cuda/pybind_module.cpp	15
optimum/quanto/library/extensions/__init__.py	20
optimum/quanto/library/extensions/hip/__init__.py	14
optimum/quanto/library/extensions/hip/unpack.cu	77
optimum/quanto/library/extensions/hip/unpack.h	2
optimum/quanto/library/extensions/hip/pybind_module.cpp	5
optimum/quanto/library/extensions/xpu/__init__.py	18
optimum/quanto/library/extensions/xpu/unpack.h	2
optimum/quanto/library/extensions/xpu/pybind_module.cpp	5
optimum/quanto/library/extensions/extension.py	54
optimum/quanto/library/extensions/mps/__init__.py	14
optimum/quanto/library/extensions/mps/unpack.h	2
optimum/quanto/library/extensions/mps/pybind_module.cpp	5
optimum/quanto/library/extensions/mps/unpack.mm	90
optimum/quanto/library/extensions/cpp/__init__.py	14
optimum/quanto/library/extensions/cpp/unpack.cpp	29
optimum/quanto/library/extensions/cpp/unpack.h	2
optimum/quanto/library/extensions/cpp/pybind_module.cpp	5
optimum/quanto/library/qbytes_mm.py	82
optimum/quanto/tensor/activations/__init__.py	2
optimum/quanto/tensor/activations/qbytes.py	57
optimum/quanto/tensor/activations/qbytes_ops.py	183
optimum/quanto/tensor/activations/quantization.py	8
optimum/quanto/tensor/grouped.py	33
optimum/quanto/tensor/qtensor.py	49
optimum/quanto/tensor/__init__.py	9
optimum/quanto/tensor/qbytes.py	23
optimum/quanto/tensor/qbits.py	39
optimum/quanto/tensor/qtype.py	32
optimum/quanto/tensor/function.py	22
optimum/quanto/tensor/packed.py	95
optimum/quanto/tensor/optimizers/__init__.py	6
optimum/quanto/tensor/optimizers/optimizer.py	9
optimum/quanto/tensor/optimizers/max_optimizer.py	17
optimum/quanto/tensor/optimizers/hqq_optimizer.py	54
optimum/quanto/tensor/optimizers/affine_optimizer.py	29
optimum/quanto/tensor/optimizers/absmax_optimizer.py	16
optimum/quanto/tensor/optimizers/symmetric_optimizer.py	16
optimum/quanto/tensor/core.py	12
optimum/quanto/tensor/weights/__init__.py	3
optimum/quanto/tensor/weights/qbytes.py	226
optimum/quanto/tensor/weights/packing.py	10
optimum/quanto/tensor/weights/marlin/__init__.py	3
optimum/quanto/tensor/weights/marlin/fp8/__init__.py	2
optimum/quanto/tensor/weights/marlin/fp8/qbits.py	102
optimum/quanto/tensor/weights/marlin/fp8/packed.py	141
optimum/quanto/tensor/weights/marlin/int4/__init__.py	2
optimum/quanto/tensor/weights/marlin/int4/qbits.py	111
optimum/quanto/tensor/weights/marlin/int4/packed.py	113
optimum/quanto/tensor/weights/marlin/permutations.py	26
optimum/quanto/tensor/weights/qbits.py	204
optimum/quanto/tensor/weights/quantization.py	29
optimum/quanto/tensor/weights/tinygemm/__init__.py	2
optimum/quanto/tensor/weights/tinygemm/qbits.py	119
optimum/quanto/tensor/weights/tinygemm/packed.py	83
optimum/quanto/tensor/weights/awq/__init__.py	2
optimum/quanto/tensor/weights/awq/qbits.py	108
optimum/quanto/tensor/weights/awq/packed.py	154
optimum/quanto/tensor/weights/reordering.py	12
optimum/quanto/nn/qlayernorm.py	32
optimum/quanto/nn/qmodule.py	217
optimum/quanto/nn/__init__.py	4
optimum/quanto/nn/qconv2d.py	34
optimum/quanto/nn/qlinear.py	29
bench/generation/metrics/__init__.py	1
bench/generation/metrics/latency.py	86
bench/generation/metrics/perplexity.py	71
bench/generation/metrics/prediction.py	24
bench/generation/gen_barchart.py	60
bench/generation/setup/__init__.py	1
bench/generation/setup/bnb.py	25
bench/generation/setup/awq.py	52
bench/generation/setup/hqq.py	19
bench/generation/setup/quanto.py	55
bench/generation/evaluate_configurations.py	88
bench/generation/evaluate_model.py	110
bench/kernels/benchmark.py	86
bench/kernels/benchmark_marlin_fp8.py	121
bench/kernels/benchmark_w4a16.py	123