LICENSE
README.md
pyproject.toml
setup.cfg
flashrnn/__init__.py
flashrnn.egg-info/PKG-INFO
flashrnn.egg-info/SOURCES.txt
flashrnn.egg-info/dependency_links.txt
flashrnn.egg-info/requires.txt
flashrnn.egg-info/top_level.txt
flashrnn/autotune/__init__.py
flashrnn/autotune/caching.py
flashrnn/autotune/constrint.py
flashrnn/autotune/runner.py
flashrnn/autotune/submit.py
flashrnn/flashrnn/__init__.py
flashrnn/flashrnn/cuda_init.py
flashrnn/flashrnn/cuda_init_parametric.py
flashrnn/flashrnn/flashrnn.py
flashrnn/flashrnn/alternating/elman_pointwise.cu
flashrnn/flashrnn/alternating/flashrnn.cc
flashrnn/flashrnn/alternating/flashrnn.h
flashrnn/flashrnn/alternating/flashrnn_backward.cu
flashrnn/flashrnn/alternating/flashrnn_backward_cut.cu
flashrnn/flashrnn/alternating/flashrnn_forward.cu
flashrnn/flashrnn/alternating/flashrnn_pointwise.cuh
flashrnn/flashrnn/alternating/gru_pointwise.cu
flashrnn/flashrnn/alternating/lstm_pointwise.cu
flashrnn/flashrnn/alternating/slstm_pointwise.cu
flashrnn/flashrnn/fused/__init__.py
flashrnn/flashrnn/fused/elman_fused_pointwise.cuh
flashrnn/flashrnn/fused/flashrnn.cc
flashrnn/flashrnn/fused/flashrnn.h
flashrnn/flashrnn/fused/flashrnn_fused_backward.cu
flashrnn/flashrnn/fused/flashrnn_fused_backward_cut.cu
flashrnn/flashrnn/fused/flashrnn_fused_forward.cu
flashrnn/flashrnn/fused/flashrnn_fused_pointwise_base.cuh
flashrnn/flashrnn/fused/gru_fused_pointwise.cuh
flashrnn/flashrnn/fused/lstm_fused_pointwise.cuh
flashrnn/flashrnn/fused/slstm_fused_pointwise.cuh
flashrnn/flashrnn/gpu_info/__init__.py
flashrnn/flashrnn/gpu_info/assign_struct.py
flashrnn/flashrnn/gpu_info/defs_cudaDeviceProperties.cc
flashrnn/flashrnn/gpu_info/gpu_info.cc
flashrnn/flashrnn/gpu_info/gpu_info.cu
flashrnn/flashrnn/gpu_info/gpu_info.h
flashrnn/flashrnn/gpu_info/gpu_info.py
flashrnn/flashrnn/gpu_info/gpu_info_test.cc
flashrnn/flashrnn/triton_fused/__init__.py
flashrnn/flashrnn/triton_fused/fwbw.py
flashrnn/flashrnn/triton_fused/lstm_bw.py
flashrnn/flashrnn/triton_fused/lstm_fw.py
flashrnn/flashrnn/triton_fused/slstm_bw.py
flashrnn/flashrnn/triton_fused/slstm_fw.py
flashrnn/flashrnn/triton_fused/triton_utils.py
flashrnn/flashrnn/util/blas.cu
flashrnn/flashrnn/util/blas.h
flashrnn/flashrnn/util/cuda_error.cu
flashrnn/flashrnn/util/cuda_error.h
flashrnn/flashrnn/util/device_assert.h
flashrnn/flashrnn/util/inline_ops.cuh
flashrnn/flashrnn/util/inline_ops_2bf16.cuh
flashrnn/flashrnn/util/inline_ops_2fp16.cuh
flashrnn/flashrnn/util/inline_ops_bf16.cuh
flashrnn/flashrnn/util/inline_ops_fp16.cuh
flashrnn/flashrnn/util/inline_print.cuh
flashrnn/flashrnn/util/support.h
flashrnn/flashrnn/util/util.h
flashrnn/flashrnn/vanilla/__init__.py
flashrnn/flashrnn/vanilla/elman.py
flashrnn/flashrnn/vanilla/gru.py
flashrnn/flashrnn/vanilla/lstm.py
flashrnn/flashrnn/vanilla/slstm.py
flashrnn/flashrnn/vanilla_fwbw/__init__.py
flashrnn/flashrnn/vanilla_fwbw/bw.py
flashrnn/flashrnn/vanilla_fwbw/fw.py
flashrnn/flashrnn/vanilla_fwbw/fwbw.py
flashrnn/speed_experiments/__init__.py
flashrnn/speed_experiments/kernel_speed_benchmark.py
flashrnn/speed_experiments/plot_config.py
flashrnn/speed_experiments/plot_results.py
flashrnn/speed_experiments/baseline_kernels/__init__.py
flashrnn/speed_experiments/baseline_kernels/torch_lstm.py
flashrnn/speed_experiments/baseline_kernels/torch_sdp_attention.py