LICENSE
README.md
setup.py
csrc/python_api.cpp
deep_gemm/__init__.py
deep_gemm.egg-info/PKG-INFO
deep_gemm.egg-info/SOURCES.txt
deep_gemm.egg-info/dependency_links.txt
deep_gemm.egg-info/not-zip-safe
deep_gemm.egg-info/top_level.txt
deep_gemm/include/deep_gemm/comm/barrier.cuh
deep_gemm/include/deep_gemm/common/compile.cuh
deep_gemm/include/deep_gemm/common/cute_tie.cuh
deep_gemm/include/deep_gemm/common/epilogue_utils.cuh
deep_gemm/include/deep_gemm/common/exception.cuh
deep_gemm/include/deep_gemm/common/math.cuh
deep_gemm/include/deep_gemm/common/reduction.cuh
deep_gemm/include/deep_gemm/common/scheduler.cuh
deep_gemm/include/deep_gemm/common/sm100_utils.cuh
deep_gemm/include/deep_gemm/common/sm90_utils.cuh
deep_gemm/include/deep_gemm/common/tma_copy.cuh
deep_gemm/include/deep_gemm/common/tma_utils.cuh
deep_gemm/include/deep_gemm/common/types.cuh
deep_gemm/include/deep_gemm/common/types.hpp
deep_gemm/include/deep_gemm/common/utils.cuh
deep_gemm/include/deep_gemm/epilogue/sm100_store_cd.cuh
deep_gemm/include/deep_gemm/epilogue/sm100_store_cd_swap_ab.cuh
deep_gemm/include/deep_gemm/epilogue/transform.cuh
deep_gemm/include/deep_gemm/impls/sm100_bf16_gemm.cuh
deep_gemm/include/deep_gemm/impls/sm100_bmk_bnk_mn.cuh
deep_gemm/include/deep_gemm/impls/sm100_fp4_mqa_logits.cuh
deep_gemm/include/deep_gemm/impls/sm100_fp4_paged_mqa_logits.cuh
deep_gemm/include/deep_gemm/impls/sm100_fp8_fp4_gemm_1d1d.cuh
deep_gemm/include/deep_gemm/impls/sm100_fp8_fp4_mega_moe.cuh
deep_gemm/include/deep_gemm/impls/sm100_fp8_gemm_1d1d.cuh
deep_gemm/include/deep_gemm/impls/sm100_fp8_mqa_logits.cuh
deep_gemm/include/deep_gemm/impls/sm100_fp8_paged_mqa_logits.cuh
deep_gemm/include/deep_gemm/impls/sm100_tf32_hc_prenorm_gemm.cuh
deep_gemm/include/deep_gemm/impls/sm90_bf16_gemm.cuh
deep_gemm/include/deep_gemm/impls/sm90_bmk_bnk_mn.cuh
deep_gemm/include/deep_gemm/impls/sm90_fp8_gemm_1d1d.cuh
deep_gemm/include/deep_gemm/impls/sm90_fp8_gemm_1d2d.cuh
deep_gemm/include/deep_gemm/impls/sm90_fp8_mqa_logits.cuh
deep_gemm/include/deep_gemm/impls/sm90_fp8_paged_mqa_logits.cuh
deep_gemm/include/deep_gemm/impls/sm90_tf32_hc_prenorm_gemm.cuh
deep_gemm/include/deep_gemm/impls/smxx_clean_logits.cuh
deep_gemm/include/deep_gemm/impls/smxx_layout.cuh
deep_gemm/include/deep_gemm/layout/mega_moe.cuh
deep_gemm/include/deep_gemm/layout/sym_buffer.cuh
deep_gemm/include/deep_gemm/mma/sm100.cuh
deep_gemm/include/deep_gemm/mma/sm90.cuh
deep_gemm/include/deep_gemm/ptx/ld_st.cuh
deep_gemm/include/deep_gemm/ptx/tcgen05.cuh
deep_gemm/include/deep_gemm/ptx/tma.cuh
deep_gemm/include/deep_gemm/ptx/utils.cuh
deep_gemm/include/deep_gemm/ptx/wgmma.cuh
deep_gemm/include/deep_gemm/scheduler/gemm.cuh
deep_gemm/include/deep_gemm/scheduler/mega_moe.cuh
deep_gemm/include/deep_gemm/scheduler/paged_mqa_logits.cuh
deep_gemm/legacy/__init__.py
deep_gemm/legacy/a_fused_k_grouped_gemm.py
deep_gemm/legacy/a_fused_m_grouped_gemm.py
deep_gemm/legacy/b_fused_k_grouped_gemm.py
deep_gemm/legacy/m_grouped_gemm.py
deep_gemm/legacy/tune_options.py
deep_gemm/mega/__init__.py
deep_gemm/testing/__init__.py
deep_gemm/testing/bench.py
deep_gemm/testing/numeric.py
deep_gemm/testing/utils.py
deep_gemm/utils/__init__.py
deep_gemm/utils/dist.py
deep_gemm/utils/layout.py
deep_gemm/utils/math.py
tests/test_attention.py
tests/test_bf16.py
tests/test_einsum.py
tests/test_fp8_fp4.py
tests/test_hyperconnection.py
tests/test_layout.py
tests/test_lazy_init.py
tests/test_legacy.py
tests/test_mega_moe.py
tests/test_sanitizer.py