LICENSE
MANIFEST.in
README.md
setup.py
exl2conv/__init__.py
exl2conv/architecture.py
exl2conv/attn.py
exl2conv/cache.py
exl2conv/compat.py
exl2conv/config.py
exl2conv/embedding.py
exl2conv/ext.py
exl2conv/fasttensors.py
exl2conv/headnorm.py
exl2conv/layernorm.py
exl2conv/linear.py
exl2conv/lora.py
exl2conv/mlp.py
exl2conv/model.py
exl2conv/model_init.py
exl2conv/module.py
exl2conv/moe_mlp.py
exl2conv/parallel_decoder.py
exl2conv/pos_embedding.py
exl2conv/rmsnorm.py
exl2conv/tokenizer.py
exl2conv/util.py
exl2conv/version.py
exl2conv.egg-info/PKG-INFO
exl2conv.egg-info/SOURCES.txt
exl2conv.egg-info/dependency_links.txt
exl2conv.egg-info/requires.txt
exl2conv.egg-info/top_level.txt
exl2conv/conversion/adaptivegptq.py
exl2conv/conversion/compile.py
exl2conv/conversion/convert.py
exl2conv/conversion/measure.py
exl2conv/conversion/optimize.py
exl2conv/conversion/qparams.py
exl2conv/conversion/quantize.py
exl2conv/conversion/tokenize.py
exl2conv/conversion/standard_cal_data/c4.utf8
exl2conv/conversion/standard_cal_data/code.utf8
exl2conv/conversion/standard_cal_data/multilingual.utf8
exl2conv/conversion/standard_cal_data/technical.utf8
exl2conv/conversion/standard_cal_data/tiny.utf8
exl2conv/conversion/standard_cal_data/wiki.utf8
exl2conv/exl2conv_ext/config.h
exl2conv/exl2conv_ext/ext_bindings.cpp
exl2conv/exl2conv_ext/ext_cache.cpp
exl2conv/exl2conv_ext/ext_cache.h
exl2conv/exl2conv_ext/ext_gemm.cpp
exl2conv/exl2conv_ext/ext_gemm.h
exl2conv/exl2conv_ext/ext_hadamard.cpp
exl2conv/exl2conv_ext/ext_hadamard.h
exl2conv/exl2conv_ext/ext_norm.cpp
exl2conv/exl2conv_ext/ext_norm.h
exl2conv/exl2conv_ext/ext_qattn.cpp
exl2conv/exl2conv_ext/ext_qattn.h
exl2conv/exl2conv_ext/ext_qmatrix.cpp
exl2conv/exl2conv_ext/ext_qmatrix.h
exl2conv/exl2conv_ext/ext_qmlp.cpp
exl2conv/exl2conv_ext/ext_qmlp.h
exl2conv/exl2conv_ext/ext_quant.cpp
exl2conv/exl2conv_ext/ext_quant.h
exl2conv/exl2conv_ext/ext_rope.cpp
exl2conv/exl2conv_ext/ext_rope.h
exl2conv/exl2conv_ext/ext_safetensors.cpp
exl2conv/exl2conv_ext/ext_safetensors.h
exl2conv/exl2conv_ext/ext_sampling.cpp
exl2conv/exl2conv_ext/ext_sampling.h
exl2conv/exl2conv_ext/cpp/avx2_target.h
exl2conv/exl2conv_ext/cpp/avx_mathfun.h
exl2conv/exl2conv_ext/cpp/generator.cpp
exl2conv/exl2conv_ext/cpp/generator.h
exl2conv/exl2conv_ext/cpp/profiling.cpp
exl2conv/exl2conv_ext/cpp/profiling.h
exl2conv/exl2conv_ext/cpp/quantize_func.cpp
exl2conv/exl2conv_ext/cpp/quantize_func.h
exl2conv/exl2conv_ext/cpp/safetensors.cpp
exl2conv/exl2conv_ext/cpp/safetensors.h
exl2conv/exl2conv_ext/cpp/sampling.cpp
exl2conv/exl2conv_ext/cpp/sampling.h
exl2conv/exl2conv_ext/cpp/sampling_avx2.cpp
exl2conv/exl2conv_ext/cpp/sampling_avx2.h
exl2conv/exl2conv_ext/cpp/util.h
exl2conv/exl2conv_ext/cuda/cache.cu
exl2conv/exl2conv_ext/cuda/cache.cuh
exl2conv/exl2conv_ext/cuda/compat.cuh
exl2conv/exl2conv_ext/cuda/h_add.cu
exl2conv/exl2conv_ext/cuda/h_add.cuh
exl2conv/exl2conv_ext/cuda/h_gemm.cu
exl2conv/exl2conv_ext/cuda/h_gemm.cuh
exl2conv/exl2conv_ext/cuda/head_norm.cu
exl2conv/exl2conv_ext/cuda/head_norm.cuh
exl2conv/exl2conv_ext/cuda/layer_norm.cu
exl2conv/exl2conv_ext/cuda/layer_norm.cuh
exl2conv/exl2conv_ext/cuda/lora.cu
exl2conv/exl2conv_ext/cuda/lora.cuh
exl2conv/exl2conv_ext/cuda/matrix_view.cuh
exl2conv/exl2conv_ext/cuda/pack_tensor.cu
exl2conv/exl2conv_ext/cuda/pack_tensor.cuh
exl2conv/exl2conv_ext/cuda/q_attn.cu
exl2conv/exl2conv_ext/cuda/q_attn.cuh
exl2conv/exl2conv_ext/cuda/q_gemm.cu
exl2conv/exl2conv_ext/cuda/q_gemm.cuh
exl2conv/exl2conv_ext/cuda/q_gemm_autotune.cuh
exl2conv/exl2conv_ext/cuda/q_gemm_kernel.cuh
exl2conv/exl2conv_ext/cuda/q_gemm_kernel_gptq.cuh
exl2conv/exl2conv_ext/cuda/q_matrix.cu
exl2conv/exl2conv_ext/cuda/q_matrix.cuh
exl2conv/exl2conv_ext/cuda/q_mlp.cu
exl2conv/exl2conv_ext/cuda/q_mlp.cuh
exl2conv/exl2conv_ext/cuda/q_mlp_activation.cuh
exl2conv/exl2conv_ext/cuda/q_mlp_softmax.cuh
exl2conv/exl2conv_ext/cuda/quantize.cu
exl2conv/exl2conv_ext/cuda/quantize.cuh
exl2conv/exl2conv_ext/cuda/rms_norm.cu
exl2conv/exl2conv_ext/cuda/rms_norm.cuh
exl2conv/exl2conv_ext/cuda/rope.cu
exl2conv/exl2conv_ext/cuda/rope.cuh
exl2conv/exl2conv_ext/cuda/util.cu
exl2conv/exl2conv_ext/cuda/util.cuh
exl2conv/exl2conv_ext/cuda/comp_units/kernel_select.cu
exl2conv/exl2conv_ext/cuda/comp_units/kernel_select.cuh
exl2conv/exl2conv_ext/cuda/comp_units/unit_exl2_1a.cu
exl2conv/exl2conv_ext/cuda/comp_units/unit_exl2_1b.cu
exl2conv/exl2conv_ext/cuda/comp_units/unit_exl2_2a.cu
exl2conv/exl2conv_ext/cuda/comp_units/unit_exl2_2b.cu
exl2conv/exl2conv_ext/cuda/comp_units/unit_exl2_3a.cu
exl2conv/exl2conv_ext/cuda/comp_units/unit_exl2_3b.cu
exl2conv/exl2conv_ext/cuda/comp_units/unit_gptq_1.cu
exl2conv/exl2conv_ext/cuda/comp_units/unit_gptq_2.cu
exl2conv/exl2conv_ext/cuda/comp_units/unit_gptq_3.cu
exl2conv/exl2conv_ext/cuda/quant/qdq_2.cuh
exl2conv/exl2conv_ext/cuda/quant/qdq_3.cuh
exl2conv/exl2conv_ext/cuda/quant/qdq_4.cuh
exl2conv/exl2conv_ext/cuda/quant/qdq_5.cuh
exl2conv/exl2conv_ext/cuda/quant/qdq_6.cuh
exl2conv/exl2conv_ext/cuda/quant/qdq_8.cuh
exl2conv/exl2conv_ext/cuda/quant/qdq_util.cuh
exl2conv/generator/__init__.py
exl2conv/generator/base.py
exl2conv/generator/hooks.py
exl2conv/generator/ngram.py
exl2conv/generator/sampler.py
exl2conv/generator/streaming.py
exl2conv/generator/filters/__init__.py
exl2conv/generator/filters/base.py
exl2conv/generator/filters/prefix.py
exl2conv/generator/filters/select.py
exl2conv/hadamard/hadamard.py
exl2conv/hadamard/hadamard_1.txt
exl2conv/hadamard/hadamard_100.txt
exl2conv/hadamard/hadamard_116.txt
exl2conv/hadamard/hadamard_156.txt
exl2conv/hadamard/hadamard_172.txt
exl2conv/hadamard/hadamard_188.txt
exl2conv/hadamard/hadamard_236.txt
exl2conv/hadamard/hadamard_244.txt
exl2conv/hadamard/hadamard_428.txt
exl2conv/hadamard/hadamard_52.txt
exl2conv/hadamard/hadamard_92.txt
exl2conv/hadamard/primes.txt
exl2conv/server/__init__.py
exl2conv/server/websocket.py
exl2conv/server/websocket_actions.py
exl2conv/tokenizer/__init__.py
exl2conv/tokenizer/base.py
exl2conv/tokenizer/hf.py
exl2conv/tokenizer/spm.py
exl2conv/tokenizer/tokenizer.py