LICENSE
MANIFEST.in
README.md
pyproject.toml
requirements-cpu.txt
requirements-hpu.txt
requirements.txt
setup.cfg
setup.py
third-party-programs.txt
auto_round/__init__.py
auto_round/__main__.py
auto_round/alg_ext.py
auto_round/autoround.py
auto_round/calib_dataset.py
auto_round/envs.py
auto_round/formats.py
auto_round/logger.py
auto_round/schemes.py
auto_round/special_model_handler.py
auto_round/version.py
auto_round/wrapper.py
auto_round/algorithms/__init__.py
auto_round/algorithms/alg_config.py
auto_round/algorithms/base.py
auto_round/algorithms/quantization/__init__.py
auto_round/algorithms/quantization/base.py
auto_round/algorithms/quantization/config.py
auto_round/algorithms/quantization/utils.py
auto_round/algorithms/quantization/adam_round/__init__.py
auto_round/algorithms/quantization/adam_round/adam.py
auto_round/algorithms/quantization/awq/__init__.py
auto_round/algorithms/quantization/awq/config.py
auto_round/algorithms/quantization/awq/mappings.py
auto_round/algorithms/quantization/awq/quantizer.py
auto_round/algorithms/quantization/rtn/__init__.py
auto_round/algorithms/quantization/rtn/config.py
auto_round/algorithms/quantization/rtn/quantizer.py
auto_round/algorithms/quantization/sign_round/__init__.py
auto_round/algorithms/quantization/sign_round/config.py
auto_round/algorithms/quantization/sign_round/quantizer.py
auto_round/algorithms/quantization/sign_round/sign_sgd.py
auto_round/algorithms/quantization/sign_roundv2/__init__.py
auto_round/algorithms/quantization/sign_roundv2/quantizer.py
auto_round/algorithms/transforms/__init__.py
auto_round/algorithms/transforms/base.py
auto_round/algorithms/transforms/rotation/__init__.py
auto_round/algorithms/transforms/rotation/apply.py
auto_round/algorithms/transforms/rotation/config.py
auto_round/algorithms/transforms/rotation/dispatcher.py
auto_round/algorithms/transforms/rotation/patch.py
auto_round/algorithms/transforms/rotation/transforms.py
auto_round/algorithms/transforms/rotation/inplace/__init__.py
auto_round/algorithms/transforms/rotation/inplace/apply.py
auto_round/algorithms/transforms/rotation/inplace/hooks.py
auto_round/algorithms/transforms/rotation/inplace/model_config.py
auto_round/algorithms/transforms/rotation/utils/__init__.py
auto_round/algorithms/transforms/rotation/utils/hadamards.safetensors
auto_round/algorithms/transforms/rotation/utils/math.py
auto_round/algorithms/transforms/rotation/utils/matrix.py
auto_round/algorithms/transforms/rotation/utils/triton/__init__.py
auto_round/algorithms/transforms/rotation/utils/triton/mxfp4.py
auto_round/algorithms/transforms/spinquant/__init__.py
auto_round/algorithms/transforms/spinquant/apply.py
auto_round/algorithms/transforms/spinquant/cayley_optimizer.py
auto_round/algorithms/transforms/spinquant/known_hadamard.py
auto_round/algorithms/transforms/spinquant/monkeypatch.py
auto_round/algorithms/transforms/spinquant/preprocessor.py
auto_round/algorithms/transforms/spinquant/rotation_utils.py
auto_round/algorithms/transforms/spinquant/serialize.py
auto_round/algorithms/transforms/spinquant/training.py
auto_round/algorithms/transforms/spinquant/inplace/__init__.py
auto_round/algorithms/transforms/spinquant/inplace/apply.py
auto_round/auto_scheme/__init__.py
auto_round/auto_scheme/delta_loss.py
auto_round/auto_scheme/gen_auto_scheme.py
auto_round/auto_scheme/register.py
auto_round/auto_scheme/utils.py
auto_round/calibration/__init__.py
auto_round/calibration/base.py
auto_round/calibration/diffusion.py
auto_round/calibration/hooks.py
auto_round/calibration/inputs.py
auto_round/calibration/llm.py
auto_round/calibration/mllm.py
auto_round/calibration/register.py
auto_round/calibration/state.py
auto_round/calibration/utils.py
auto_round/compressors/__init__.py
auto_round/compressors/base.py
auto_round/compressors/config.py
auto_round/compressors/data_driven.py
auto_round/compressors/diffusion_mixin.py
auto_round/compressors/entry.py
auto_round/compressors/mllm_mixin.py
auto_round/compressors/model_free.py
auto_round/compressors/shard_writer.py
auto_round/compressors/utils.py
auto_round/compressors/zero_shot.py
auto_round/compressors/diffusion/__init__.py
auto_round/compressors/diffusion/dataset.py
auto_round/compressors/diffusion/eval.py
auto_round/compressors/mllm/__init__.py
auto_round/compressors/mllm/dataset.py
auto_round/compressors/mllm/processor.py
auto_round/compressors/mllm/template.py
auto_round/compressors/mllm/utils.py
auto_round/compressors/mllm/templates/cogvlm2.json
auto_round/compressors/mllm/templates/default.json
auto_round/compressors/mllm/templates/llava.json
auto_round/compressors/mllm/templates/phi3_v.json
auto_round/context/__init__.py
auto_round/context/base.py
auto_round/context/compress.py
auto_round/context/model.py
auto_round/data_type/__init__.py
auto_round/data_type/fp8.py
auto_round/data_type/gguf.py
auto_round/data_type/int.py
auto_round/data_type/mxfp.py
auto_round/data_type/nvfp.py
auto_round/data_type/register.py
auto_round/data_type/utils.py
auto_round/data_type/w4fp8.py
auto_round/eval/__init__.py
auto_round/eval/eval_cli.py
auto_round/eval/evaluation.py
auto_round/experimental/__init__.py
auto_round/experimental/apply_rotation_transform.py
auto_round/experimental/attention.py
auto_round/experimental/kv_cache.py
auto_round/experimental/utils.py
auto_round/experimental/qmodules/__init__.py
auto_round/experimental/qmodules/base.py
auto_round/experimental/qmodules/fp4_utils.py
auto_round/experimental/qmodules/fp8_static.py
auto_round/experimental/qmodules/mx.py
auto_round/experimental/qmodules/mxint4_utils.py
auto_round/experimental/qmodules/nvfp4.py
auto_round/export/__init__.py
auto_round/export/utils.py
auto_round/export/export_to_autogptq/__init__.py
auto_round/export/export_to_autogptq/export.py
auto_round/export/export_to_autoround/__init__.py
auto_round/export/export_to_autoround/export.py
auto_round/export/export_to_autoround/export_to_fp8.py
auto_round/export/export_to_autoround/export_to_nvfp_mx.py
auto_round/export/export_to_autoround/qlinear_fp.py
auto_round/export/export_to_autoround/qlinear_int.py
auto_round/export/export_to_autoround/qlinear_triton_act.py
auto_round/export/export_to_autoround/utils.py
auto_round/export/export_to_awq/__init__.py
auto_round/export/export_to_awq/export.py
auto_round/export/export_to_awq/utils.py
auto_round/export/export_to_gguf/__init__.py
auto_round/export/export_to_gguf/config.py
auto_round/export/export_to_gguf/convert.py
auto_round/export/export_to_gguf/export.py
auto_round/export/export_to_gguf/gguf_dtype.py
auto_round/export/export_to_gguf/llama_cpp_conversion.py
auto_round/export/export_to_gguf/packing.py
auto_round/export/export_to_gguf/special_handle.py
auto_round/export/export_to_gguf/sync_llama_cpp_conversion.py
auto_round/export/export_to_gguf/conversion/__init__.py
auto_round/export/export_to_gguf/conversion/afmoe.py
auto_round/export/export_to_gguf/conversion/arctic.py
auto_round/export/export_to_gguf/conversion/baichuan.py
auto_round/export/export_to_gguf/conversion/bailingmoe.py
auto_round/export/export_to_gguf/conversion/base.py
auto_round/export/export_to_gguf/conversion/bert.py
auto_round/export/export_to_gguf/conversion/bitnet.py
auto_round/export/export_to_gguf/conversion/bloom.py
auto_round/export/export_to_gguf/conversion/chameleon.py
auto_round/export/export_to_gguf/conversion/chatglm.py
auto_round/export/export_to_gguf/conversion/codeshell.py
auto_round/export/export_to_gguf/conversion/cogvlm.py
auto_round/export/export_to_gguf/conversion/command_r.py
auto_round/export/export_to_gguf/conversion/dbrx.py
auto_round/export/export_to_gguf/conversion/deci.py
auto_round/export/export_to_gguf/conversion/deepseek.py
auto_round/export/export_to_gguf/conversion/dots1.py
auto_round/export/export_to_gguf/conversion/dotsocr.py
auto_round/export/export_to_gguf/conversion/dream.py
auto_round/export/export_to_gguf/conversion/ernie.py
auto_round/export/export_to_gguf/conversion/exaone.py
auto_round/export/export_to_gguf/conversion/falcon.py
auto_round/export/export_to_gguf/conversion/falcon_h1.py
auto_round/export/export_to_gguf/conversion/gemma.py
auto_round/export/export_to_gguf/conversion/glm.py
auto_round/export/export_to_gguf/conversion/gpt2.py
auto_round/export/export_to_gguf/conversion/gpt_oss.py
auto_round/export/export_to_gguf/conversion/gptneox.py
auto_round/export/export_to_gguf/conversion/granite.py
auto_round/export/export_to_gguf/conversion/grok.py
auto_round/export/export_to_gguf/conversion/grovemoe.py
auto_round/export/export_to_gguf/conversion/hunyuan.py
auto_round/export/export_to_gguf/conversion/internlm.py
auto_round/export/export_to_gguf/conversion/internvl.py
auto_round/export/export_to_gguf/conversion/jais.py
auto_round/export/export_to_gguf/conversion/jamba.py
auto_round/export/export_to_gguf/conversion/januspro.py
auto_round/export/export_to_gguf/conversion/kimi_linear.py
auto_round/export/export_to_gguf/conversion/kimivl.py
auto_round/export/export_to_gguf/conversion/lfm2.py
auto_round/export/export_to_gguf/conversion/lighton_ocr.py
auto_round/export/export_to_gguf/conversion/llada.py
auto_round/export/export_to_gguf/conversion/llama.py
auto_round/export/export_to_gguf/conversion/llama4.py
auto_round/export/export_to_gguf/conversion/llava.py
auto_round/export/export_to_gguf/conversion/maincoder.py
auto_round/export/export_to_gguf/conversion/mamba.py
auto_round/export/export_to_gguf/conversion/mimo.py
auto_round/export/export_to_gguf/conversion/minicpm.py
auto_round/export/export_to_gguf/conversion/minimax.py
auto_round/export/export_to_gguf/conversion/mistral.py
auto_round/export/export_to_gguf/conversion/mistral3.py
auto_round/export/export_to_gguf/conversion/mpt.py
auto_round/export/export_to_gguf/conversion/nemotron.py
auto_round/export/export_to_gguf/conversion/olmo.py
auto_round/export/export_to_gguf/conversion/openelm.py
auto_round/export/export_to_gguf/conversion/orion.py
auto_round/export/export_to_gguf/conversion/pangu.py
auto_round/export/export_to_gguf/conversion/phi.py
auto_round/export/export_to_gguf/conversion/pixtral.py
auto_round/export/export_to_gguf/conversion/plamo.py
auto_round/export/export_to_gguf/conversion/plm.py
auto_round/export/export_to_gguf/conversion/qwen.py
auto_round/export/export_to_gguf/conversion/qwen3vl.py
auto_round/export/export_to_gguf/conversion/qwenvl.py
auto_round/export/export_to_gguf/conversion/refact.py
auto_round/export/export_to_gguf/conversion/rwkv.py
auto_round/export/export_to_gguf/conversion/sarashina2.py
auto_round/export/export_to_gguf/conversion/smallthinker.py
auto_round/export/export_to_gguf/conversion/smolvlm.py
auto_round/export/export_to_gguf/conversion/stablelm.py
auto_round/export/export_to_gguf/conversion/starcoder.py
auto_round/export/export_to_gguf/conversion/step3.py
auto_round/export/export_to_gguf/conversion/t5.py
auto_round/export/export_to_gguf/conversion/ultravox.py
auto_round/export/export_to_gguf/conversion/wavtokenizer.py
auto_round/export/export_to_gguf/conversion/xverse.py
auto_round/export/export_to_gguf/conversion/youtuvl.py
auto_round/export/export_to_llmcompressor/__init__.py
auto_round/export/export_to_llmcompressor/config.py
auto_round/export/export_to_llmcompressor/export.py
auto_round/export/export_to_llmcompressor/export_to_fp.py
auto_round/export/export_to_llmcompressor/export_to_static_fp.py
auto_round/export/export_to_llmcompressor/utils.py
auto_round/export/export_to_mlx/__init__.py
auto_round/export/export_to_mlx/export.py
auto_round/inference/__init__.py
auto_round/inference/backend.py
auto_round/inference/convert_model.py
auto_round/inference/utils.py
auto_round/modeling/__init__.py
auto_round/modeling/finegrained_fp8_patch.py
auto_round/modeling/finegrained_fp8_patch_v4.py
auto_round/modeling/fp8_quant.py
auto_round/modeling/hpu_patch.py
auto_round/modeling/fused_moe/__init__.py
auto_round/modeling/fused_moe/deepseek_v2.py
auto_round/modeling/fused_moe/gpt_oss.py
auto_round/modeling/fused_moe/llama4.py
auto_round/modeling/fused_moe/moe_experts_interface.py
auto_round/modeling/fused_moe/qwen3_5_moe.py
auto_round/modeling/fused_moe/qwen3_omni.py
auto_round/modeling/fused_moe/qwen3_vl_moe.py
auto_round/modeling/fused_moe/replace_modules.py
auto_round/modeling/fused_moe/step3_5_moe.py
auto_round/modeling/fused_moe/utils.py
auto_round/modeling/unfused_moe/__init__.py
auto_round/modeling/unfused_moe/deepseek_v3.py
auto_round/modeling/unfused_moe/ernie4_5_moe.py
auto_round/modeling/unfused_moe/glm_moe.py
auto_round/modeling/unfused_moe/glm_moe_dsa.py
auto_round/modeling/unfused_moe/glm_moe_light.py
auto_round/modeling/unfused_moe/qwen3_moe.py
auto_round/modeling/unfused_moe/qwen3_next.py
auto_round/utils/__init__.py
auto_round/utils/bagel_loader.py
auto_round/utils/common.py
auto_round/utils/device.py
auto_round/utils/device_manager.py
auto_round/utils/distributed.py
auto_round/utils/missing_tensors.py
auto_round/utils/model.py
auto_round/utils/offload.py
auto_round/utils/weight_handler.py
auto_round_extension/__init__.py
auto_round_extension/cuda/__init__.py
auto_round_extension/cuda/gptqmodel_marlin.py
auto_round_extension/hpu/__init__.py
auto_round_extension/hpu/qlinear_hpu.py
auto_round_extension/hpu/qlinear_hpu_gptq.py
auto_round_extension/mlx/__init__.py
auto_round_extension/mlx/qlinear_mlx.py
auto_round_extension/torch/__init__.py
auto_round_extension/torch/qlinear_mlx.py
auto_round_extension/torch/qlinear_torch.py
auto_round_extension/torch/qlinear_torch_zp.py
auto_round_extension/triton/__init__.py
auto_round_extension/triton/qlinear_tritonv2.py
auto_round_extension/triton/qlinear_tritonv2_zp.py
auto_round_extension/triton/triton_utils/__init__.py
auto_round_extension/triton/triton_utils/custom_autotune.py
auto_round_extension/triton/triton_utils/dequant.py
auto_round_extension/triton/triton_utils/kernels.py
auto_round_extension/triton/triton_utils/mixin.py
auto_round_extension/triton/triton_utils_zp/__init__.py
auto_round_extension/triton/triton_utils_zp/custom_autotune.py
auto_round_extension/triton/triton_utils_zp/dequant.py
auto_round_extension/triton/triton_utils_zp/kernels.py
auto_round_extension/triton/triton_utils_zp/mixin.py
auto_round_extension/vllm_ext/__init__.py
auto_round_extension/vllm_ext/auto_round_ext.py
auto_round_extension/vllm_ext/envs_ext.py
auto_round_extension/vllm_ext/fp4_utils.py
auto_round_extension/vllm_ext/kv_cache.py
auto_round_extension/vllm_ext/linear_impl_mxfp4.py
auto_round_extension/vllm_ext/linear_impl_mxfp8.py
auto_round_extension/vllm_ext/moe_impl_mxfp4.py
auto_round_extension/vllm_ext/moe_impl_mxfp8.py
auto_round_extension/vllm_ext/mxfp4_qdq_utils.py
auto_round_extension/vllm_ext/mxfp8_qdq_utils.py
auto_round_extension/vllm_ext/quant_impl.py
auto_round_extension/vllm_ext/quant_method_linear.py
auto_round_extension/vllm_ext/quant_method_moe.py
auto_round_extension/vllm_ext/sitecustomize.py
auto_round_extension/vllm_ext/utils.py
auto_round_extension/vllm_ext/vllm_oot_patches.py
auto_round_nightly.egg-info/PKG-INFO
auto_round_nightly.egg-info/SOURCES.txt
auto_round_nightly.egg-info/dependency_links.txt
auto_round_nightly.egg-info/entry_points.txt
auto_round_nightly.egg-info/requires.txt
auto_round_nightly.egg-info/top_level.txt