LICENSE
README.md
pyproject.toml
setup.py
tilefoundry_nvidia/__init__.py
tilefoundry_nvidia.egg-info/PKG-INFO
tilefoundry_nvidia.egg-info/SOURCES.txt
tilefoundry_nvidia.egg-info/dependency_links.txt
tilefoundry_nvidia.egg-info/entry_points.txt
tilefoundry_nvidia.egg-info/requires.txt
tilefoundry_nvidia.egg-info/scm_file_list.json
tilefoundry_nvidia.egg-info/scm_version.json
tilefoundry_nvidia.egg-info/top_level.txt
tilefoundry_nvidia/cuda/__init__.py
tilefoundry_nvidia/cuda/codegen/__init__.py
tilefoundry_nvidia/cuda/codegen/abi.py
tilefoundry_nvidia/cuda/codegen/context.py
tilefoundry_nvidia/cuda/codegen/emit.py
tilefoundry_nvidia/cuda/codegen/host_launch.py
tilefoundry_nvidia/cuda/codegen/module.py
tilefoundry_nvidia/cuda/codegen/hir/__init__.py
tilefoundry_nvidia/cuda/codegen/hir/function.py
tilefoundry_nvidia/cuda/codegen/include/tilefoundry/runtime/cuda/runtime.cuh
tilefoundry_nvidia/cuda/codegen/include/tilefoundry/runtime/cuda/layout/cute_ext.cuh
tilefoundry_nvidia/cuda/codegen/include/tilefoundry/runtime/cuda/layout/mesh.cuh
tilefoundry_nvidia/cuda/codegen/include/tilefoundry/runtime/cuda/layout/shard_layout.cuh
tilefoundry_nvidia/cuda/codegen/include/tilefoundry/runtime/cuda/ops/copy.cuh
tilefoundry_nvidia/cuda/codegen/include/tilefoundry/runtime/cuda/ops/copy_async_bulk.cuh
tilefoundry_nvidia/cuda/codegen/include/tilefoundry/runtime/cuda/ops/detail.cuh
tilefoundry_nvidia/cuda/codegen/include/tilefoundry/runtime/cuda/ops/dot.cuh
tilefoundry_nvidia/cuda/codegen/include/tilefoundry/runtime/cuda/ops/elementwise.cuh
tilefoundry_nvidia/cuda/codegen/include/tilefoundry/runtime/cuda/ops/ldmatrix.cuh
tilefoundry_nvidia/cuda/codegen/include/tilefoundry/runtime/cuda/ops/mma.cuh
tilefoundry_nvidia/cuda/codegen/include/tilefoundry/runtime/cuda/ops/reduce.cuh
tilefoundry_nvidia/cuda/codegen/include/tilefoundry/runtime/cuda/ops/sync.cuh
tilefoundry_nvidia/cuda/codegen/include/tilefoundry/runtime/cuda/ops/copy/copy_impl.h
tilefoundry_nvidia/cuda/codegen/include/tilefoundry/runtime/cuda/ops/copy_async_bulk/copy_async_bulk_impl.h
tilefoundry_nvidia/cuda/codegen/include/tilefoundry/runtime/cuda/ops/dot/dot_impl.h
tilefoundry_nvidia/cuda/codegen/include/tilefoundry/runtime/cuda/ops/elementwise/elementwise_impl.h
tilefoundry_nvidia/cuda/codegen/include/tilefoundry/runtime/cuda/ops/ldmatrix/ldmatrix_impl.h
tilefoundry_nvidia/cuda/codegen/include/tilefoundry/runtime/cuda/ops/mma/mma_impl.h
tilefoundry_nvidia/cuda/codegen/include/tilefoundry/runtime/cuda/ops/reduce/reduce_common_impl.h
tilefoundry_nvidia/cuda/codegen/include/tilefoundry/runtime/cuda/ops/reduce/reduce_cross_warp_impl.h
tilefoundry_nvidia/cuda/codegen/include/tilefoundry/runtime/cuda/ops/reduce/reduce_intra_cta_impl.h
tilefoundry_nvidia/cuda/codegen/include/tilefoundry/runtime/cuda/ops/reduce/reduce_intra_warp_impl.h
tilefoundry_nvidia/cuda/codegen/include/tilefoundry/runtime/cuda/ops/reduce/reduce_plain_impl.h
tilefoundry_nvidia/cuda/codegen/include/tilefoundry/runtime/cuda/ops/sync/sync_impl.h
tilefoundry_nvidia/cuda/codegen/include/tilefoundry/runtime/cuda/primitive/binary.h
tilefoundry_nvidia/cuda/codegen/include/tilefoundry/runtime/cuda/primitive/unary.h
tilefoundry_nvidia/cuda/codegen/include/tilefoundry/runtime/cuda/tensor_view/shard_tensor.cuh
tilefoundry_nvidia/cuda/codegen/include/tilefoundry/runtime/cuda/utility/warp.cuh
tilefoundry_nvidia/cuda/codegen/templates/__init__.py
tilefoundry_nvidia/cuda/codegen/templates/cuda_preamble.cu.j2
tilefoundry_nvidia/cuda/codegen/tir/__init__.py
tilefoundry_nvidia/cuda/codegen/tir/arith.py
tilefoundry_nvidia/cuda/codegen/tir/async_copy.py
tilefoundry_nvidia/cuda/codegen/tir/clamp.py
tilefoundry_nvidia/cuda/codegen/tir/cute_layout.py
tilefoundry_nvidia/cuda/codegen/tir/dot.py
tilefoundry_nvidia/cuda/codegen/tir/mbarrier.py
tilefoundry_nvidia/cuda/codegen/tir/prim_function.py
tilefoundry_nvidia/cuda/codegen/tir/reduce.py
tilefoundry_nvidia/cuda/codegen/tir/sync.py
tilefoundry_nvidia/cuda/codegen/tir/tuple_get_item.py
tilefoundry_nvidia/cuda/codegen/tir/memory/__init__.py
tilefoundry_nvidia/cuda/codegen/tir/memory/alloc_tensor.py
tilefoundry_nvidia/cuda/codegen/tir/memory/copy.py
tilefoundry_nvidia/cuda/codegen/tir/memory/copy_async_bulk.py
tilefoundry_nvidia/cuda/codegen/tir/memory/copy_async_tensor.py
tilefoundry_nvidia/cuda/codegen/tir/memory/copy_reduce_async_tensor.py
tilefoundry_nvidia/cuda/codegen/tir/memory/fill.py
tilefoundry_nvidia/cuda/codegen/tir/memory/ldmatrix.py
tilefoundry_nvidia/cuda/codegen/tir/memory/ptr_of.py
tilefoundry_nvidia/cuda/codegen/tir/memory/stmatrix.py
tilefoundry_nvidia/cuda/codegen/tir/memory/tensor_view.py
tilefoundry_nvidia/cuda/codegen/tir/nn/__init__.py
tilefoundry_nvidia/cuda/codegen/tir/nn/mma.py
tilefoundry_nvidia/cuda/codegen/tir/nn/relu.py
tilefoundry_nvidia/cuda/codegen/tir/stmts/__init__.py
tilefoundry_nvidia/cuda/codegen/tir/stmts/mesh_scope.py
tilefoundry_nvidia/cuda/docs/spec/cli.md
tilefoundry_nvidia/cuda/docs/spec/codegen.md
tilefoundry_nvidia/cuda/docs/spec/hir.md
tilefoundry_nvidia/cuda/docs/spec/passes.md
tilefoundry_nvidia/cuda/docs/spec/runtime.md
tilefoundry_nvidia/cuda/docs/spec/target.md
tilefoundry_nvidia/cuda/docs/spec/tir.md
tilefoundry_nvidia/cuda/ir/__init__.py
tilefoundry_nvidia/cuda/ir/hir/__init__.py
tilefoundry_nvidia/cuda/ir/hir/nn/__init__.py
tilefoundry_nvidia/cuda/ir/hir/nn/matmul.py
tilefoundry_nvidia/cuda/ir/tir/__init__.py
tilefoundry_nvidia/cuda/ir/tir/launch.py
tilefoundry_nvidia/cuda/ir/tir/memory/__init__.py
tilefoundry_nvidia/cuda/ir/tir/memory/copy_async_bulk.py
tilefoundry_nvidia/cuda/ir/tir/memory/copy_async_tensor.py
tilefoundry_nvidia/cuda/ir/tir/memory/copy_reduce_async_tensor.py
tilefoundry_nvidia/cuda/ir/tir/memory/ldmatrix.py
tilefoundry_nvidia/cuda/ir/tir/memory/stmatrix.py
tilefoundry_nvidia/cuda/ir/tir/nn/__init__.py
tilefoundry_nvidia/cuda/ir/tir/nn/mma.py
tilefoundry_nvidia/cuda/ir/tir/nn/mma_atom.py
tilefoundry_nvidia/cuda/ir/tir/nn/sm80_mma.py
tilefoundry_nvidia/cuda/ir/tir/nn/sm89_mma.py
tilefoundry_nvidia/cuda/ir/tir/nn/wgmma.py
tilefoundry_nvidia/cuda/ir/tir/sync/__init__.py
tilefoundry_nvidia/cuda/ir/tir/sync/mbarrier.py
tilefoundry_nvidia/cuda/models/catalog.json
tilefoundry_nvidia/cuda/models/deepseek_v4_flash/config.json
tilefoundry_nvidia/cuda/models/deepseek_v4_flash/model.py
tilefoundry_nvidia/cuda/models/gemma2_2b/config.json
tilefoundry_nvidia/cuda/models/gemma2_2b/hf_alias.py
tilefoundry_nvidia/cuda/models/gemma2_2b/model.py
tilefoundry_nvidia/cuda/models/kimi_linear_48b_a3b/config.json
tilefoundry_nvidia/cuda/models/kimi_linear_48b_a3b/model.py
tilefoundry_nvidia/cuda/models/minicpm3_4b/config.json
tilefoundry_nvidia/cuda/models/minicpm3_4b/hf_alias.py
tilefoundry_nvidia/cuda/models/minicpm3_4b/model.py
tilefoundry_nvidia/cuda/models/qwen2_5_1_5b/config.json
tilefoundry_nvidia/cuda/models/qwen2_5_1_5b/hf_alias.py
tilefoundry_nvidia/cuda/models/qwen2_5_1_5b/model.py
tilefoundry_nvidia/cuda/models/qwen3_1_7b/config.json
tilefoundry_nvidia/cuda/models/qwen3_1_7b/hf_alias.py
tilefoundry_nvidia/cuda/models/qwen3_1_7b/model.py
tilefoundry_nvidia/cuda/models/qwen3_5_35b_a3b/config.json
tilefoundry_nvidia/cuda/models/qwen3_5_35b_a3b/hf_alias.py
tilefoundry_nvidia/cuda/models/qwen3_5_35b_a3b/model.py
tilefoundry_nvidia/cuda/passes/__init__.py
tilefoundry_nvidia/cuda/passes/transforms/__init__.py
tilefoundry_nvidia/cuda/passes/transforms/host_entry.py
tilefoundry_nvidia/cuda/target/__init__.py
tilefoundry_nvidia/cuda/target/architecture.py
tilefoundry_nvidia/cuda/target/device.py
tilefoundry_nvidia/cuda/target/facts.py
tilefoundry_nvidia/cuda/target/spec.py
tilefoundry_nvidia/cuda/target/target.py
tilefoundry_nvidia/cuda/target/hardware/__init__.py
tilefoundry_nvidia/cuda/target/hardware/nvidia_b200_sxm.toml
tilefoundry_nvidia/cuda/target/hardware/nvidia_h200_sxm.toml
tilefoundry_nvidia/cuda/target/hardware/nvidia_rtx_6000_ada.toml
tilefoundry_nvidia/cuda/target/hardware/nvidia_sm100.toml
tilefoundry_nvidia/cuda/target/hardware/nvidia_sm89.toml
tilefoundry_nvidia/cuda/target/hardware/nvidia_sm90.toml
tilefoundry_nvidia/cuda/visitor_registry/__init__.py
tilefoundry_nvidia/cuda/visitor_registry/candidates.py