Commit 9da50c0
committed
1 file changed
+1
-1
lines changed- README.md+4-2
- csrc/apis/gemm.hpp+537
- csrc/apis/layout.hpp+85
- csrc/apis/runtime.hpp+28
- csrc/jit/compiler.hpp+6-4
- csrc/jit/device_runtime.hpp+4-2
- csrc/jit/handle.hpp+1-1
- csrc/jit/kernel_runtime.hpp+2-2
- csrc/jit_kernels/heuristics/common.hpp+16-10
- csrc/jit_kernels/heuristics/sm100.hpp+2-2
- csrc/jit_kernels/heuristics/sm90.hpp+7-3
- csrc/jit_kernels/impls/runtime_utils.hpp+2
- csrc/jit_kernels/impls/sm100_bf16_gemm.hpp+143
- csrc/jit_kernels/impls/sm100_fp8_gemm_1d1d.hpp+24-14
- csrc/jit_kernels/impls/sm100_fp8_gemm_1d2d.hpp+3-2
- csrc/jit_kernels/impls/sm90_bf16_gemm.hpp+229
- csrc/jit_kernels/impls/sm90_fp8_gemm_1d2d.hpp+3-2
- csrc/jit_kernels/impls/smxx_layout.hpp+55-8
- csrc/python_api.cpp+6-399
- csrc/utils/exception.hpp+10-3
- deep_gemm/__init__.py+39-12
- deep_gemm/include/deep_gemm/common/scheduler.cuh+6-5
- deep_gemm/include/deep_gemm/common/sm90_utils.cuh+98
- deep_gemm/include/deep_gemm/common/utils.cuh+34
- deep_gemm/include/deep_gemm/impls/sm100_bf16_gemm.cuh+495-1
- deep_gemm/include/deep_gemm/impls/sm100_fp8_gemm_1d1d.cuh+115-44
- deep_gemm/include/deep_gemm/impls/sm100_fp8_gemm_1d2d.cuh+8-5
- deep_gemm/include/deep_gemm/impls/sm90_bf16_gemm.cuh+341-1
- deep_gemm/include/deep_gemm/impls/sm90_fp8_gemm_1d2d.cuh+1-1
- deep_gemm/include/deep_gemm/impls/smxx_layout.cuh+39
- pyproject.toml-3
- setup.py+4
- tests/generators.py+48-27
- tests/test_bf16.py+125
- tests/test_fp8.py+51-4
- tests/test_layout.py+29-17
- tests/test_lazy_init.py+15
0 commit comments