.MAINTAINERS
.gitignore
.readthedocs.yaml
CITATION.cff
CODE_OF_CONDUCT.md
CONTRIBUTING.md
DEVELOPING.md
LICENSE
MANIFEST.in
Makefile
NOTICE
README.md
mkdocs.yml
pyproject.toml
setup.py
.github/PULL_REQUEST_TEMPLATE.md
.github/TODO.txt
.github/ISSUE_TEMPLATE/bug_report.md
.github/ISSUE_TEMPLATE/doc-edit.md
.github/ISSUE_TEMPLATE/feature_request.md
.github/actions/prepare-code-coverage/action.yml
.github/workflows/build-and-publish-release-images.yaml
.github/workflows/linkcheck.yml
.github/workflows/quality-check.yaml
.github/workflows/result.xml.fail
.github/workflows/result.xml.success
.github/workflows/set-comment.yaml
.github/workflows/test-check-transformers.yaml
.github/workflows/test-check.yaml
.github/workflows/linkspector/linkspector.yml
docs/index.md
docs/observers.md
docs/assets/llmcompressor-icon-white.png
docs/assets/llmcompressor-icon.png
docs/assets/llmcompressor-user-flows.png
docs/developer/index.md
docs/examples/index.md
docs/getting-started/compress.md
docs/getting-started/deploy.md
docs/getting-started/index.md
docs/getting-started/install.md
docs/guides/compression_schemes.md
docs/guides/index.md
docs/guides/saving_a_model.md
docs/scripts/__init__.py
docs/scripts/gen_files.py
docs/scripts/mathjax.js
docs/stylesheets/style.css
examples/awq/README.md
examples/awq/llama_example.py
examples/awq/qwen3_moe_example.py
examples/big_models_with_sequential_onloading/README.md
examples/big_models_with_sequential_onloading/llama3.3_70b.py
examples/big_models_with_sequential_onloading/assets/sequential_onloading.png
examples/compressed_inference/fp8_compressed_inference.py
examples/finetuning/configure_fsdp.md
examples/finetuning/example_alternating_recipe.yaml
examples/finetuning/example_fsdp_config.yaml
examples/finetuning/example_single_gpu_config.yaml
examples/multimodal_audio/README.md
examples/multimodal_audio/whisper_example.py
examples/multimodal_vision/README.md
examples/multimodal_vision/gemma3_example.py
examples/multimodal_vision/idefics3_example.py
examples/multimodal_vision/llama4_example.py
examples/multimodal_vision/llava_example.py
examples/multimodal_vision/mistral3_chat_template.json
examples/multimodal_vision/mistral3_example.py
examples/multimodal_vision/mllama_example.py
examples/multimodal_vision/phi3_vision_example.py
examples/multimodal_vision/pixtral_example.py
examples/multimodal_vision/qwen2_vl_example.py
examples/multimodal_vision/qwen_2_5_vl_example.py
examples/quantization_2of4_sparse_w4a16/2of4_w4a16_group-128_recipe.yaml
examples/quantization_2of4_sparse_w4a16/2of4_w4a16_recipe.yaml
examples/quantization_2of4_sparse_w4a16/README.md
examples/quantization_2of4_sparse_w4a16/llama7b_sparse_w4a16.py
examples/quantization_kv_cache/README.md
examples/quantization_kv_cache/gemma2_fp8_kv_example.py
examples/quantization_kv_cache/llama3_fp8_kv_example.py
examples/quantization_kv_cache/phi3.5_fp8_kv_example.py
examples/quantization_w4a16/README.md
examples/quantization_w4a16/llama3_example.py
examples/quantization_w4a16_fp4/llama3_example.py
examples/quantization_w4a16_fp4/qwen3_example.py
examples/quantization_w4a4_fp4/llama3_example.py
examples/quantization_w4a4_fp4/llama4_example.py
examples/quantization_w4a4_fp4/qwen_30b_a3b.py
examples/quantization_w8a8_fp8/README.md
examples/quantization_w8a8_fp8/fp8_block_example.py
examples/quantization_w8a8_fp8/gemma2_example.py
examples/quantization_w8a8_fp8/llama3.2_vision_example.py
examples/quantization_w8a8_fp8/llama3_example.py
examples/quantization_w8a8_fp8/llava1.5_example.py
examples/quantization_w8a8_fp8/qwen2vl_example.py
examples/quantization_w8a8_fp8/whisper_example.py
examples/quantization_w8a8_int8/README.md
examples/quantization_w8a8_int8/gemma2_example.py
examples/quantization_w8a8_int8/llama3_example.py
examples/quantizing_moe/README.md
examples/quantizing_moe/deepseek_moe_w4a16.py
examples/quantizing_moe/deepseek_moe_w8a8_fp8.py
examples/quantizing_moe/deepseek_moe_w8a8_int8.py
examples/quantizing_moe/deepseek_r1_example.py
examples/quantizing_moe/deepseek_recipe_w4a16.yaml
examples/quantizing_moe/mixtral_moe_w8a8_fp8.py
examples/quantizing_moe/qwen_moe_w4a16.py
examples/sparse_2of4_quantization_fp8/README.md
examples/sparse_2of4_quantization_fp8/llama3_8b_2of4.py
examples/trl_mixin/README.md
examples/trl_mixin/ex_trl_constant.py
examples/trl_mixin/ex_trl_distillation.py
examples/trl_mixin/sft_trainer.py
experimental/mistral/README.md
experimental/mistral/fp8_quantize.py
src/llmcompressor/__init__.py
src/llmcompressor/logger.py
src/llmcompressor/sentinel.py
src/llmcompressor/typing.py
src/llmcompressor/version.py
src/llmcompressor.egg-info/PKG-INFO
src/llmcompressor.egg-info/SOURCES.txt
src/llmcompressor.egg-info/dependency_links.txt
src/llmcompressor.egg-info/entry_points.txt
src/llmcompressor.egg-info/requires.txt
src/llmcompressor.egg-info/top_level.txt
src/llmcompressor/args/README.md
src/llmcompressor/args/__init__.py
src/llmcompressor/args/dataset_arguments.py
src/llmcompressor/args/model_arguments.py
src/llmcompressor/args/recipe_arguments.py
src/llmcompressor/args/training_arguments.py
src/llmcompressor/args/utils.py
src/llmcompressor/core/__init__.py
src/llmcompressor/core/helpers.py
src/llmcompressor/core/lifecycle.py
src/llmcompressor/core/model_layer.py
src/llmcompressor/core/session.py
src/llmcompressor/core/session_functions.py
src/llmcompressor/core/state.py
src/llmcompressor/core/events/__init__.py
src/llmcompressor/core/events/event.py
src/llmcompressor/datasets/__init__.py
src/llmcompressor/datasets/utils.py
src/llmcompressor/entrypoints/README.md
src/llmcompressor/entrypoints/__init__.py
src/llmcompressor/entrypoints/oneshot.py
src/llmcompressor/entrypoints/train.py
src/llmcompressor/entrypoints/utils.py
src/llmcompressor/metrics/__init__.py
src/llmcompressor/metrics/logger.py
src/llmcompressor/metrics/utils/__init__.py
src/llmcompressor/metrics/utils/frequency_manager.py
src/llmcompressor/modeling/__init__.py
src/llmcompressor/modeling/deepseek_v3.py
src/llmcompressor/modeling/fuse.py
src/llmcompressor/modeling/llama4.py
src/llmcompressor/modeling/prepare.py
src/llmcompressor/modeling/qwen3_moe.py
src/llmcompressor/modifiers/README.md
src/llmcompressor/modifiers/__init__.py
src/llmcompressor/modifiers/factory.py
src/llmcompressor/modifiers/interface.py
src/llmcompressor/modifiers/modifier.py
src/llmcompressor/modifiers/awq/__init__.py
src/llmcompressor/modifiers/awq/base.py
src/llmcompressor/modifiers/awq/mappings.py
src/llmcompressor/modifiers/distillation/__init__.py
src/llmcompressor/modifiers/distillation/output/__init__.py
src/llmcompressor/modifiers/distillation/output/base.py
src/llmcompressor/modifiers/distillation/utils/__init__.py
src/llmcompressor/modifiers/distillation/utils/pytorch/__init__.py
src/llmcompressor/modifiers/distillation/utils/pytorch/kd_factory.py
src/llmcompressor/modifiers/distillation/utils/pytorch/kd_wrapper.py
src/llmcompressor/modifiers/distillation/utils/pytorch/model_wrapper.py
src/llmcompressor/modifiers/experimental/__init__.py
src/llmcompressor/modifiers/logarithmic_equalization/__init__.py
src/llmcompressor/modifiers/logarithmic_equalization/base.py
src/llmcompressor/modifiers/obcq/__init__.py
src/llmcompressor/modifiers/obcq/base.py
src/llmcompressor/modifiers/obcq/sgpt_base.py
src/llmcompressor/modifiers/obcq/sgpt_sparsify.py
src/llmcompressor/modifiers/pruning/__init__.py
src/llmcompressor/modifiers/pruning/helpers.py
src/llmcompressor/modifiers/pruning/constant/__init__.py
src/llmcompressor/modifiers/pruning/constant/base.py
src/llmcompressor/modifiers/pruning/magnitude/__init__.py
src/llmcompressor/modifiers/pruning/magnitude/base.py
src/llmcompressor/modifiers/pruning/utils/__init__.py
src/llmcompressor/modifiers/pruning/utils/pytorch/__init__.py
src/llmcompressor/modifiers/pruning/utils/pytorch/layer_mask.py
src/llmcompressor/modifiers/pruning/utils/pytorch/mask_factory.py
src/llmcompressor/modifiers/pruning/wanda/__init__.py
src/llmcompressor/modifiers/pruning/wanda/base.py
src/llmcompressor/modifiers/pruning/wanda/wanda_sparsify.py
src/llmcompressor/modifiers/quantization/__init__.py
src/llmcompressor/modifiers/quantization/cache.py
src/llmcompressor/modifiers/quantization/calibration.py
src/llmcompressor/modifiers/quantization/gptq/__init__.py
src/llmcompressor/modifiers/quantization/gptq/base.py
src/llmcompressor/modifiers/quantization/gptq/gptq_quantize.py
src/llmcompressor/modifiers/quantization/quantization/__init__.py
src/llmcompressor/modifiers/quantization/quantization/base.py
src/llmcompressor/modifiers/quantization/quantization/mixin.py
src/llmcompressor/modifiers/smoothquant/README.md
src/llmcompressor/modifiers/smoothquant/__init__.py
src/llmcompressor/modifiers/smoothquant/base.py
src/llmcompressor/modifiers/smoothquant/utils.py
src/llmcompressor/modifiers/utils/__init__.py
src/llmcompressor/modifiers/utils/constants.py
src/llmcompressor/modifiers/utils/helpers.py
src/llmcompressor/modifiers/utils/hooks.py
src/llmcompressor/modifiers/utils/pytorch_helpers.py
src/llmcompressor/observers/__init__.py
src/llmcompressor/observers/base.py
src/llmcompressor/observers/helpers.py
src/llmcompressor/observers/min_max.py
src/llmcompressor/observers/mse.py
src/llmcompressor/pipelines/__init__.py
src/llmcompressor/pipelines/cache.py
src/llmcompressor/pipelines/registry.py
src/llmcompressor/pipelines/basic/__init__.py
src/llmcompressor/pipelines/basic/pipeline.py
src/llmcompressor/pipelines/data_free/__init__.py
src/llmcompressor/pipelines/data_free/pipeline.py
src/llmcompressor/pipelines/independent/__init__.py
src/llmcompressor/pipelines/independent/pipeline.py
src/llmcompressor/pipelines/layer_sequential/__init__.py
src/llmcompressor/pipelines/layer_sequential/helpers.py
src/llmcompressor/pipelines/layer_sequential/pipeline.py
src/llmcompressor/pipelines/sequential/README.md
src/llmcompressor/pipelines/sequential/__init__.py
src/llmcompressor/pipelines/sequential/ast_helpers.py
src/llmcompressor/pipelines/sequential/helpers.py
src/llmcompressor/pipelines/sequential/pipeline.py
src/llmcompressor/pipelines/sequential/ast_utils/auto_wrapper.py
src/llmcompressor/pipelines/sequential/ast_utils/control_flow_analyzer.py
src/llmcompressor/pipelines/sequential/ast_utils/name_analyzer.py
src/llmcompressor/pytorch/__init__.py
src/llmcompressor/pytorch/model_load/__init__.py
src/llmcompressor/pytorch/model_load/helpers.py
src/llmcompressor/pytorch/utils/__init__.py
src/llmcompressor/pytorch/utils/helpers.py
src/llmcompressor/pytorch/utils/sparsification.py
src/llmcompressor/pytorch/utils/sparsification_info/__init__.py
src/llmcompressor/pytorch/utils/sparsification_info/configs.py
src/llmcompressor/pytorch/utils/sparsification_info/helpers.py
src/llmcompressor/pytorch/utils/sparsification_info/module_sparsification_info.py
src/llmcompressor/recipe/__init__.py
src/llmcompressor/recipe/metadata.py
src/llmcompressor/recipe/recipe.py
src/llmcompressor/recipe/utils.py
src/llmcompressor/transformers/__init__.py
src/llmcompressor/transformers/compression/__init__.py
src/llmcompressor/transformers/compression/helpers.py
src/llmcompressor/transformers/compression/quantization_format.py
src/llmcompressor/transformers/compression/sparsity_metadata_config.py
src/llmcompressor/transformers/finetune/README.md
src/llmcompressor/transformers/finetune/__init__.py
src/llmcompressor/transformers/finetune/callbacks.py
src/llmcompressor/transformers/finetune/session_mixin.py
src/llmcompressor/transformers/finetune/text_generation.py
src/llmcompressor/transformers/finetune/trainer.py
src/llmcompressor/transformers/finetune/data/__init__.py
src/llmcompressor/transformers/finetune/data/base.py
src/llmcompressor/transformers/finetune/data/c4.py
src/llmcompressor/transformers/finetune/data/cnn_dailymail.py
src/llmcompressor/transformers/finetune/data/custom.py
src/llmcompressor/transformers/finetune/data/data_helpers.py
src/llmcompressor/transformers/finetune/data/evolcodealpaca.py
src/llmcompressor/transformers/finetune/data/flickr_30k.py
src/llmcompressor/transformers/finetune/data/gsm8k.py
src/llmcompressor/transformers/finetune/data/open_platypus.py
src/llmcompressor/transformers/finetune/data/peoples_speech.py
src/llmcompressor/transformers/finetune/data/ultrachat_200k.py
src/llmcompressor/transformers/finetune/data/wikitext.py
src/llmcompressor/transformers/sparsification/__init__.py
src/llmcompressor/transformers/sparsification/compressed_tensors_utils.py
src/llmcompressor/transformers/sparsification/sparse_model.py
src/llmcompressor/transformers/tracing/__init__.py
src/llmcompressor/transformers/tracing/debug.py
src/llmcompressor/transformers/utils/__init__.py
src/llmcompressor/transformers/utils/helpers.py
src/llmcompressor/transformers/utils/preprocessing_functions.py
src/llmcompressor/utils/__init__.py
src/llmcompressor/utils/dev.py
src/llmcompressor/utils/helpers.py
src/llmcompressor/utils/metric_logging.py
src/llmcompressor/utils/fsdp/__init__.py
src/llmcompressor/utils/fsdp/context.py
src/llmcompressor/utils/fsdp/helpers.py
src/llmcompressor/utils/pytorch/__init__.py
src/llmcompressor/utils/pytorch/module.py
src/llmcompressor/utils/pytorch/utils.py
tests/__init__.py
tests/custom_test.py
tests/data.py
tests/testing_utils.py
tests/e2e/__init__.py
tests/e2e/e2e_utils.py
tests/e2e/vLLM/__init__.py
tests/e2e/vLLM/run_tests.sh
tests/e2e/vLLM/test_vllm.py
tests/e2e/vLLM/configs/fp4_nvfp4.yaml
tests/e2e/vLLM/configs/fp4_nvfp4a16.yaml
tests/e2e/vLLM/configs/fp8_dynamic_per_token.yaml
tests/e2e/vLLM/configs/fp8_dynamic_per_token_qwen.yaml
tests/e2e/vLLM/configs/fp8_static_per_tensor.yaml
tests/e2e/vLLM/configs/fp8_weight_only_channel.yaml
tests/e2e/vLLM/configs/fp8_weight_only_tensor.yaml
tests/e2e/vLLM/configs/int8_channel_weight_static_per_tensor_act.yaml
tests/e2e/vLLM/configs/int8_dynamic_per_token.yaml
tests/e2e/vLLM/configs/int8_tensor_weight_static_per_tensor_act.yaml
tests/e2e/vLLM/configs/int8_tensor_weight_static_per_tensor_act_qwen.yaml
tests/e2e/vLLM/configs/kv_cache_gptq_tinyllama.yaml
tests/e2e/vLLM/configs/kv_cache_phi3.yaml
tests/e2e/vLLM/configs/kv_cache_tinyllama.yaml
tests/e2e/vLLM/configs/sparse2of4_fp8_dynamic.yaml
tests/e2e/vLLM/configs/sparse2of4_fp8_dynamic_qwen.yaml
tests/e2e/vLLM/configs/sparse_24.yaml
tests/e2e/vLLM/configs/w4a16_2of4_channel_quant.yaml
tests/e2e/vLLM/configs/w4a16_2of4_grouped_quant.yaml
tests/e2e/vLLM/configs/w4a16_actorder_group.yaml
tests/e2e/vLLM/configs/w4a16_actorder_group_qwen.yaml
tests/e2e/vLLM/configs/w4a16_actorder_weight.yaml
tests/e2e/vLLM/configs/w4a16_actorder_weight_qwen.yaml
tests/e2e/vLLM/configs/w4a16_channel_quant.yaml
tests/e2e/vLLM/configs/w4a16_channel_quant_qwen.yaml
tests/e2e/vLLM/configs/w4a16_grouped_quant.yaml
tests/e2e/vLLM/configs/w4a16_grouped_quant_asym_awq.yaml
tests/e2e/vLLM/configs/w8a16_channel_quant.yaml
tests/e2e/vLLM/configs/w8a16_grouped_quant.yaml
tests/e2e/vLLM/configs/w8a8_dynamic_asym.yaml
tests/e2e/vLLM/configs/w8a8_static_asym.yaml
tests/e2e/vLLM/recipes/FP8/recipe_fp8_dynamic.yaml
tests/e2e/vLLM/recipes/FP8/recipe_fp8_weight_only_channel.yaml
tests/e2e/vLLM/recipes/FP8/recipe_fp8_weight_only_per_tensor.yaml
tests/e2e/vLLM/recipes/INT8/recipe_int8_channel_weight_dynamic_per_token.yaml
tests/e2e/vLLM/recipes/INT8/recipe_int8_channel_weight_static_per_tensor_act.yaml
tests/e2e/vLLM/recipes/INT8/recipe_int8_tensor_weight_static_per_tensor_act.yaml
tests/e2e/vLLM/recipes/INT8/recipe_w8a8_dynamic_asym.yaml
tests/e2e/vLLM/recipes/INT8/recipe_w8a8_static_asym.yaml
tests/e2e/vLLM/recipes/Sparse_2of4/recipe_sparse_2of4.yaml
tests/e2e/vLLM/recipes/Sparse_2of4/recipe_sparse_2of4_fp8_dynamic.yaml
tests/e2e/vLLM/recipes/WNA16/recipe_w4a16_channel_quant.yaml
tests/e2e/vLLM/recipes/WNA16/recipe_w4a16_group_quant_asym_awq.yaml
tests/e2e/vLLM/recipes/WNA16/recipe_w8a16_channel_quant.yaml
tests/e2e/vLLM/recipes/WNA16_2of4/2of4_w4a16_group-128_recipe.yaml
tests/e2e/vLLM/recipes/WNA16_2of4/2of4_w4a16_recipe.yaml
tests/e2e/vLLM/recipes/actorder/recipe_w4a16_actorder_group.yaml
tests/e2e/vLLM/recipes/actorder/recipe_w4a16_actorder_weight.yaml
tests/e2e/vLLM/recipes/kv_cache/default.yaml
tests/e2e/vLLM/recipes/kv_cache/gptq.yaml
tests/examples/__init__.py
tests/examples/test_compressed_inference.py
tests/examples/test_quantization_2of4_sparse_w4a16.py
tests/examples/test_quantization_kv_cache.py
tests/examples/test_quantization_w4a16.py
tests/examples/test_quantization_w8a8_fp8.py
tests/examples/test_quantization_w8a8_int8.py
tests/examples/test_quantizing_moe.py
tests/examples/test_sparse_2of4_quantization_fp8.py
tests/examples/test_trl_mixin.py
tests/examples/utils.py
tests/llmcompressor/__init__.py
tests/llmcompressor/conftest.py
tests/llmcompressor/helpers.py
tests/llmcompressor/test_sentinel.py
tests/llmcompressor/metrics/__init__.py
tests/llmcompressor/metrics/test_logger.py
tests/llmcompressor/metrics/utils/__init__.py
tests/llmcompressor/metrics/utils/test_frequency_manager.py
tests/llmcompressor/modeling/test_fuse.py
tests/llmcompressor/modifiers/__init__.py
tests/llmcompressor/modifiers/conf.py
tests/llmcompressor/modifiers/awq/__init__.py
tests/llmcompressor/modifiers/awq/test_base.py
tests/llmcompressor/modifiers/calibration/__init__.py
tests/llmcompressor/modifiers/calibration/test_cache.py
tests/llmcompressor/modifiers/calibration/test_frozen.py
tests/llmcompressor/modifiers/calibration/test_kv_cache.py
tests/llmcompressor/modifiers/calibration/test_observers.py
tests/llmcompressor/modifiers/logarithmic_equalization/__init__.py
tests/llmcompressor/modifiers/logarithmic_equalization/test_base.py
tests/llmcompressor/modifiers/pruning/__init__.py
tests/llmcompressor/modifiers/pruning/sparsegpt/__init__.py
tests/llmcompressor/modifiers/pruning/sparsegpt/test_base.py
tests/llmcompressor/modifiers/pruning/wanda/__init__.py
tests/llmcompressor/modifiers/pruning/wanda/test_base.py
tests/llmcompressor/modifiers/quantization/__init__.py
tests/llmcompressor/modifiers/quantization/test_base.py
tests/llmcompressor/modifiers/smoothquant/__init__.py
tests/llmcompressor/modifiers/smoothquant/test_base.py
tests/llmcompressor/modifiers/smoothquant/test_utils.py
tests/llmcompressor/modifiers/utils/test_hooks.py
tests/llmcompressor/observers/__init__.py
tests/llmcompressor/observers/test_helpers.py
tests/llmcompressor/observers/test_min_max.py
tests/llmcompressor/observers/test_mse.py
tests/llmcompressor/pipelines/test_cache.py
tests/llmcompressor/pipelines/sequential/test_helpers.py
tests/llmcompressor/pipelines/sequential/ast_utils.py/test_auto_wrapper.py
tests/llmcompressor/pytorch/__init__.py
tests/llmcompressor/pytorch/helpers.py
tests/llmcompressor/pytorch/modifiers/__init__.py
tests/llmcompressor/pytorch/modifiers/logarithmic_equalization/__init__.py
tests/llmcompressor/pytorch/modifiers/logarithmic_equalization/test_pytorch.py
tests/llmcompressor/pytorch/modifiers/pruning/__init__.py
tests/llmcompressor/pytorch/modifiers/pruning/constant/__init__.py
tests/llmcompressor/pytorch/modifiers/pruning/constant/test_pytorch.py
tests/llmcompressor/pytorch/modifiers/pruning/sparsegpt/__init__.py
tests/llmcompressor/pytorch/modifiers/pruning/sparsegpt/test_pytorch.py
tests/llmcompressor/pytorch/modifiers/pruning/wanda/test_pytorch.py
tests/llmcompressor/pytorch/modifiers/smoothquant/__init__.py
tests/llmcompressor/pytorch/modifiers/smoothquant/test_pytorch.py
tests/llmcompressor/pytorch/utils/__init__.py
tests/llmcompressor/pytorch/utils/test_helpers.py
tests/llmcompressor/pytorch/utils/test_sparse.py
tests/llmcompressor/recipe/__init__.py
tests/llmcompressor/recipe/recipe.yaml
tests/llmcompressor/recipe/test_recipe.py
tests/llmcompressor/recipe/test_recipe_parsing.py
tests/llmcompressor/transformers/__init__.py
tests/llmcompressor/transformers/conftest.py
tests/llmcompressor/transformers/compression/__init__.py
tests/llmcompressor/transformers/compression/test_decompress.py
tests/llmcompressor/transformers/compression/test_has_gpu.py
tests/llmcompressor/transformers/compression/test_helpers.py
tests/llmcompressor/transformers/compression/test_infer_quant_format.py
tests/llmcompressor/transformers/compression/test_quantization.py
tests/llmcompressor/transformers/compression/test_run_compressed.py
tests/llmcompressor/transformers/compression/test_sparsity_metadata_config.py
tests/llmcompressor/transformers/compression/configs/actorder_group_1.1b.yaml
tests/llmcompressor/transformers/compression/configs/actorder_weight_1.1b.yaml
tests/llmcompressor/transformers/compression/configs/channelwise_1.1b.yaml
tests/llmcompressor/transformers/compression/configs/channelwise_15m.yaml
tests/llmcompressor/transformers/compression/configs/fp8_1.1b.yaml
tests/llmcompressor/transformers/compression/configs/fp8_15m.yaml
tests/llmcompressor/transformers/compression/configs/group_1.1b.yaml
tests/llmcompressor/transformers/compression/configs/inputs_1.1b.yaml
tests/llmcompressor/transformers/compression/configs/inputs_15m.yaml
tests/llmcompressor/transformers/compression/configs/weights_only_1.1b.yaml
tests/llmcompressor/transformers/compression/configs/weights_only_15m.yaml
tests/llmcompressor/transformers/compression/decompression_configs/fp8_dynamic.yaml
tests/llmcompressor/transformers/compression/decompression_configs/w4a16.yaml
tests/llmcompressor/transformers/compression/decompression_configs/w8a16_dense.yaml
tests/llmcompressor/transformers/compression/decompression_configs_skipped/w8a8.yaml
tests/llmcompressor/transformers/compression/recipes/new_quant_actorder_group.yaml
tests/llmcompressor/transformers/compression/recipes/new_quant_actorder_weight.yaml
tests/llmcompressor/transformers/compression/recipes/new_quant_channel.yaml
tests/llmcompressor/transformers/compression/recipes/new_quant_fp8.yaml
tests/llmcompressor/transformers/compression/recipes/new_quant_full.yaml
tests/llmcompressor/transformers/compression/recipes/new_quant_group.yaml
tests/llmcompressor/transformers/compression/recipes/new_quant_simple.yaml
tests/llmcompressor/transformers/compression/recipes/new_quant_weight.yaml
tests/llmcompressor/transformers/compression/recipes/sparse_24.yaml
tests/llmcompressor/transformers/compression/recipes/sparse_24_fp8.yaml
tests/llmcompressor/transformers/compression/run_compressed_configs/fp8_dynamic.yaml
tests/llmcompressor/transformers/compression/run_compressed_configs/w4a16.yaml
tests/llmcompressor/transformers/compression/run_compressed_configs/w8a16.yaml
tests/llmcompressor/transformers/compression/run_compressed_configs_skipped/w8a8.yaml
tests/llmcompressor/transformers/finetune/__init__.py
tests/llmcompressor/transformers/finetune/test_alternate_recipe.yaml
tests/llmcompressor/transformers/finetune/test_finetune_no_recipe_custom_dataset.py
tests/llmcompressor/transformers/finetune/test_finetune_recipe.yaml
tests/llmcompressor/transformers/finetune/test_finetune_without_recipe.py
tests/llmcompressor/transformers/finetune/test_oneshot_and_finetune.py
tests/llmcompressor/transformers/finetune/test_oneshot_and_finetune_with_tokenizer.py
tests/llmcompressor/transformers/finetune/test_oneshot_then_finetune.py
tests/llmcompressor/transformers/finetune/test_quantization.yaml
tests/llmcompressor/transformers/finetune/test_safetensors.py
tests/llmcompressor/transformers/finetune/test_session_mixin.py
tests/llmcompressor/transformers/finetune/data/__init__.py
tests/llmcompressor/transformers/finetune/data/conftest.py
tests/llmcompressor/transformers/finetune/data/test_dataset_helpers.py
tests/llmcompressor/transformers/finetune/data/test_dataset_loading.py
tests/llmcompressor/transformers/finetune/data/test_registry.py
tests/llmcompressor/transformers/finetune/finetune_custom/config1.yaml
tests/llmcompressor/transformers/finetune/finetune_custom/config2.yaml
tests/llmcompressor/transformers/finetune/finetune_custom/gpu/gpu_config.yaml
tests/llmcompressor/transformers/finetune/finetune_generic/config1.yaml
tests/llmcompressor/transformers/finetune/finetune_oneshot_configs/config.yaml
tests/llmcompressor/transformers/finetune/finetune_oneshot_configs/gpu/gpu_config.yaml
tests/llmcompressor/transformers/finetune/finetune_tokenizer/config1.yaml
tests/llmcompressor/transformers/gptq/test_oneshot.py
tests/llmcompressor/transformers/kv_cache/test_kv_cache.py
tests/llmcompressor/transformers/obcq/__init__.py
tests/llmcompressor/transformers/obcq/test_consecutive_runs.py
tests/llmcompressor/transformers/obcq/test_mask_structure_preservation.py
tests/llmcompressor/transformers/obcq/test_obcq_completion.py
tests/llmcompressor/transformers/obcq/test_obcq_infer_targets.py
tests/llmcompressor/transformers/obcq/test_obcq_lm_head.py
tests/llmcompressor/transformers/obcq/test_obcq_owl.py
tests/llmcompressor/transformers/obcq/test_obcq_sparsity.py
tests/llmcompressor/transformers/obcq/test_oneshot_with_modifier.py
tests/llmcompressor/transformers/obcq/obcq_configs/completion/tiny_llama_quant.yaml
tests/llmcompressor/transformers/obcq/obcq_configs/completion/tiny_llama_quant_and_sparse.yaml
tests/llmcompressor/transformers/obcq/obcq_configs/completion/gpu/llama_7b_quant.yaml
tests/llmcompressor/transformers/obcq/obcq_configs/completion/gpu/llama_7b_quant_and_sparse.yaml
tests/llmcompressor/transformers/obcq/obcq_configs/completion/gpu/llama_7b_sparse.yml
tests/llmcompressor/transformers/obcq/obcq_configs/consec_runs/tiny_llama_consec_runs.yaml
tests/llmcompressor/transformers/obcq/obcq_configs/consec_runs/gpu/llama_consec_runs.yaml
tests/llmcompressor/transformers/obcq/obcq_configs/mask_structure/tiny_llama_mask_structure_preservation.yaml
tests/llmcompressor/transformers/obcq/obcq_configs/sparse/tiny_llama_sparse.yaml
tests/llmcompressor/transformers/obcq/obcq_configs/sparse/gpu/llama_7b_sparse.yaml
tests/llmcompressor/transformers/obcq/obcq_configs/sparsity_generic/config.yaml
tests/llmcompressor/transformers/obcq/recipes/additional_sparsity.yaml
tests/llmcompressor/transformers/obcq/recipes/additional_sparsity_with_quant.yaml
tests/llmcompressor/transformers/obcq/recipes/quant.yaml
tests/llmcompressor/transformers/obcq/recipes/quant_and_sparse.yaml
tests/llmcompressor/transformers/obcq/recipes/sparse.yaml
tests/llmcompressor/transformers/obcq/recipes/sparse_with_mask_structure.yaml
tests/llmcompressor/transformers/obcq/recipes/test_tiny2.yaml
tests/llmcompressor/transformers/oneshot/__init__.py
tests/llmcompressor/transformers/oneshot/dataset_processing.py
tests/llmcompressor/transformers/oneshot/test_api_inputs.py
tests/llmcompressor/transformers/oneshot/oneshot_configs/tiny_stories_conf1.yaml
tests/llmcompressor/transformers/oneshot/oneshot_configs/tiny_stories_conf2.yaml
tests/llmcompressor/transformers/oneshot/oneshot_configs/tiny_stories_conf3.yaml
tests/llmcompressor/transformers/oneshot/oneshot_configs/tiny_stories_conf4.yaml
tests/llmcompressor/transformers/oneshot/oneshot_configs/tiny_stories_conf5.yaml
tests/llmcompressor/transformers/oneshot/oneshot_configs/tiny_stories_conf6.yaml
tests/llmcompressor/transformers/oneshot/oneshot_configs/recipes/recipe.yaml
tests/llmcompressor/transformers/sparsification/__init__.py
tests/llmcompressor/transformers/sparsification/test_compress_tensor_utils.py
tests/llmcompressor/transformers/tracing/test_models.py
tests/llmcompressor/utils/__init__.py
tests/llmcompressor/utils/test_helpers.py
tests/llmcompressor/utils/pytorch/__init__.py
tests/llmcompressor/utils/pytorch/test_module.py
tests/lmeval/__init__.py
tests/lmeval/test_lmeval.py
tests/lmeval/configs/fp8_dynamic_per_token.yaml
tests/lmeval/configs/fp8_static_per_tensor.yaml
tests/lmeval/configs/int8_w8a8_dynamic_per_token.yaml
tests/lmeval/configs/vl_fp8_dynamic_per_token.yaml
tests/lmeval/configs/vl_int8_w8a8_dynamic_per_token.yaml
tests/lmeval/configs/vl_w4a16_actorder_weight.yaml
tests/lmeval/configs/w4a16_actorder_group.yaml
tests/lmeval/configs/w4a16_actorder_weight.yaml
tests/lmeval/configs/w4a16_grouped_quant.yaml
tests/test_timer/__init__.py
tests/test_timer/timer.py
tests/test_timer/timer_utils.py
tests/unit/__init__.py
tests/unit/test_logger.py
tests/unit/core/__init__.py
tests/unit/core/test_state.py
tests/unit/core/events/__init__.py
tests/unit/core/events/test_event.py