.clang-format
.gitignore
.gitmodules
.pre-commit-config.yaml
CONTRIBUTING.md
Dockerfile
LICENSE
MANIFEST.in
README.md
codecov.yml
pyproject.toml
setup.py
.github/pull_request_template.md
.github/ISSUE_TEMPLATE/config.yml
.github/ISSUE_TEMPLATE/report.md
.github/workflows/ci.yml
.github/workflows/pr-title.yml
.github/workflows/release.yml
docs/SPEC-RULES.md
docs/develop.md
docs/plans/TEMPLATE.md
docs/policies/policy.schema.json
docs/policies/project-policy.json
docs/reports/issue-237-validation.md
docs/spec/analysis.md
docs/spec/architecture.md
docs/spec/cli.md
docs/spec/code-organization.md
docs/spec/codegen.md
docs/spec/core-ir.md
docs/spec/evaluator.md
docs/spec/hir.md
docs/spec/inspection.md
docs/spec/parser.md
docs/spec/passes.md
docs/spec/runtime.md
docs/spec/schedule.md
docs/spec/semantic-analysis.md
docs/spec/shard.md
docs/spec/target.md
docs/spec/tir.md
docs/spec/types.md
docs/spec/visitor-mutator.md
docs/spec/visitor-registry.md
docs/tutorial/index.md
docs/tutorial/migrate.ipynb
docs/tutorial/migrate.md
docs/tutorial/optimize.ipynb
docs/tutorial/optimize.md
docs/tutorial/schedule.ipynb
docs/tutorial/schedule.md
docs/tutorial/showcase.ipynb
docs/tutorial/showcase.md
scripts/comment_hygiene_lint.py
scripts/english_only_lint.py
scripts/fetch_viewer_assets.py
scripts/finalize_plan_context.py
scripts/forward_references_lint.py
scripts/generate_model_catalog.py
scripts/get_policy.py
scripts/no_machine_paths_lint.py
scripts/render_tutorial.py
scripts/runtime_spec_surface.py
scripts/spec_entropy_lint.py
scripts/spec_refs_lint.py
scripts/spec_rules_lint.py
src/tilefoundry/__init__.py
src/tilefoundry/compile.py
src/tilefoundry/module.py
src/tilefoundry/script.py
src/tilefoundry.egg-info/PKG-INFO
src/tilefoundry.egg-info/SOURCES.txt
src/tilefoundry.egg-info/dependency_links.txt
src/tilefoundry.egg-info/entry_points.txt
src/tilefoundry.egg-info/requires.txt
src/tilefoundry.egg-info/scm_file_list.json
src/tilefoundry.egg-info/scm_version.json
src/tilefoundry.egg-info/top_level.txt
src/tilefoundry/analysis/__init__.py
src/tilefoundry/analysis/access.py
src/tilefoundry/analysis/allocation.py
src/tilefoundry/analysis/api.py
src/tilefoundry/analysis/check.py
src/tilefoundry/analysis/compute_cost.py
src/tilefoundry/analysis/errors.py
src/tilefoundry/analysis/facts.py
src/tilefoundry/analysis/footprint.py
src/tilefoundry/analysis/iteration_scope.py
src/tilefoundry/analysis/liveness.py
src/tilefoundry/analysis/loop_domain.py
src/tilefoundry/analysis/memory.py
src/tilefoundry/analysis/metadata.py
src/tilefoundry/analysis/performance.py
src/tilefoundry/analysis/precision.py
src/tilefoundry/analysis/registry.py
src/tilefoundry/analysis/report.py
src/tilefoundry/analysis/roofline.py
src/tilefoundry/analysis/visitor.py
src/tilefoundry/cli/__init__.py
src/tilefoundry/cli/__main__.py
src/tilefoundry/cli/analyze.py
src/tilefoundry/cli/check.py
src/tilefoundry/cli/data.py
src/tilefoundry/cli/models.py
src/tilefoundry/cli/scaffold.py
src/tilefoundry/cli/schedule.py
src/tilefoundry/cli/source.py
src/tilefoundry/cli/spec.py
src/tilefoundry/cli/target.py
src/tilefoundry/cli/tutorial.py
src/tilefoundry/codegen/__init__.py
src/tilefoundry/codegen/context.py
src/tilefoundry/codegen/context_builder.py
src/tilefoundry/codegen/emitter.py
src/tilefoundry/codegen/link_function.py
src/tilefoundry/codegen/link_module.py
src/tilefoundry/codegen/linkable_function.py
src/tilefoundry/codegen/linkable_module.py
src/tilefoundry/codegen/linked_function.py
src/tilefoundry/codegen/linked_module.py
src/tilefoundry/codegen/options.py
src/tilefoundry/codegen/scalar_expr.py
src/tilefoundry/codegen/signature.py
src/tilefoundry/codegen/cpu/__init__.py
src/tilefoundry/codegen/cpu/abi.py
src/tilefoundry/codegen/cpu/context.py
src/tilefoundry/codegen/cpu/module.py
src/tilefoundry/codegen/cpu/templates/__init__.py
src/tilefoundry/codegen/cpu/templates/cpu_entry.cpp.j2
src/tilefoundry/codegen/cpu/templates/cpu_preamble.cpp.j2
src/tilefoundry/codegen/templates/cmake/CMakeLists.txt.j2
src/tilefoundry/dsl/__init__.py
src/tilefoundry/dsl/__main__.py
src/tilefoundry/dsl/_namespace.py
src/tilefoundry/dsl/_stub_gen.py
src/tilefoundry/dsl/_tensor.py
src/tilefoundry/dsl/py.typed
src/tilefoundry/dsl/storage.py
src/tilefoundry/dsl/T/__init__.py
src/tilefoundry/dsl/tf/__init__.py
src/tilefoundry/dump/__init__.py
src/tilefoundry/dump/dumpers.py
src/tilefoundry/dump/flags.py
src/tilefoundry/dump/scope.py
src/tilefoundry/evaluator/__init__.py
src/tilefoundry/evaluator/context.py
src/tilefoundry/evaluator/dim.py
src/tilefoundry/evaluator/interpreter.py
src/tilefoundry/evaluator/kernels.py
src/tilefoundry/evaluator/registry.py
src/tilefoundry/evaluator/value.py
src/tilefoundry/inspection/__init__.py
src/tilefoundry/inspection/analysis_report.py
src/tilefoundry/inspection/dot.py
src/tilefoundry/inspection/mesh_utils.py
src/tilefoundry/inspection/pattern_printer.py
src/tilefoundry/inspection/print_context.py
src/tilefoundry/inspection/printer_base.py
src/tilefoundry/inspection/python_printer.py
src/tilefoundry/inspection/tir_printer.py
src/tilefoundry/inspection/values.py
src/tilefoundry/inspection/viewer/__init__.py
src/tilefoundry/inspection/viewer/assets.py
src/tilefoundry/inspection/viewer/builder.py
src/tilefoundry/inspection/viewer/htmltable.py
src/tilefoundry/inspection/viewer/palette.py
src/tilefoundry/inspection/viewer/server.py
src/tilefoundry/inspection/viewer/static/.gitignore
src/tilefoundry/inspection/viewer/static/index.html
src/tilefoundry/inspection/viewer/static/viewer.js
src/tilefoundry/ir/__init__.py
src/tilefoundry/ir/isl_interop.py
src/tilefoundry/ir/mesh_scope.py
src/tilefoundry/ir/module_utils.py
src/tilefoundry/ir/visitor.py
src/tilefoundry/ir/clause/__init__.py
src/tilefoundry/ir/clause/base.py
src/tilefoundry/ir/clause/layout.py
src/tilefoundry/ir/clause/mesh.py
src/tilefoundry/ir/clause/storage.py
src/tilefoundry/ir/core/__init__.py
src/tilefoundry/ir/core/context.py
src/tilefoundry/ir/core/errors.py
src/tilefoundry/ir/core/expr.py
src/tilefoundry/ir/core/inspection.py
src/tilefoundry/ir/core/kinds.py
src/tilefoundry/ir/core/metadata.py
src/tilefoundry/ir/core/module.py
src/tilefoundry/ir/core/op.py
src/tilefoundry/ir/core/op_registry.py
src/tilefoundry/ir/core/op_schema.py
src/tilefoundry/ir/core/param_def.py
src/tilefoundry/ir/core/register.py
src/tilefoundry/ir/core/static_eval.py
src/tilefoundry/ir/core/stmt.py
src/tilefoundry/ir/core/values.py
src/tilefoundry/ir/hir/__init__.py
src/tilefoundry/ir/hir/_helpers.py
src/tilefoundry/ir/hir/_shard_checks.py
src/tilefoundry/ir/hir/function.py
src/tilefoundry/ir/hir/loop_region.py
src/tilefoundry/ir/hir/mesh_region.py
src/tilefoundry/ir/hir/schedule.py
src/tilefoundry/ir/hir/specialize.py
src/tilefoundry/ir/hir/math/__init__.py
src/tilefoundry/ir/hir/math/aliases.py
src/tilefoundry/ir/hir/math/binary.py
src/tilefoundry/ir/hir/math/clamp.py
src/tilefoundry/ir/hir/math/softplus.py
src/tilefoundry/ir/hir/math/unary.py
src/tilefoundry/ir/hir/nn/__init__.py
src/tilefoundry/ir/hir/nn/conv2d.py
src/tilefoundry/ir/hir/nn/gelu.py
src/tilefoundry/ir/hir/nn/layer_norm.py
src/tilefoundry/ir/hir/nn/matmul.py
src/tilefoundry/ir/hir/nn/relu.py
src/tilefoundry/ir/hir/nn/rms_norm.py
src/tilefoundry/ir/hir/nn/rope.py
src/tilefoundry/ir/hir/nn/sigmoid.py
src/tilefoundry/ir/hir/nn/silu.py
src/tilefoundry/ir/hir/nn/softmax.py
src/tilefoundry/ir/hir/nn/tanh.py
src/tilefoundry/ir/hir/sharding/__init__.py
src/tilefoundry/ir/hir/sharding/local.py
src/tilefoundry/ir/hir/sharding/mesh_coord.py
src/tilefoundry/ir/hir/sharding/reshard.py
src/tilefoundry/ir/hir/tensor/__init__.py
src/tilefoundry/ir/hir/tensor/_view_layout.py
src/tilefoundry/ir/hir/tensor/arange.py
src/tilefoundry/ir/hir/tensor/argmax.py
src/tilefoundry/ir/hir/tensor/bitcast.py
src/tilefoundry/ir/hir/tensor/cache_update.py
src/tilefoundry/ir/hir/tensor/cast.py
src/tilefoundry/ir/hir/tensor/concat.py
src/tilefoundry/ir/hir/tensor/empty.py
src/tilefoundry/ir/hir/tensor/full_like.py
src/tilefoundry/ir/hir/tensor/index_add.py
src/tilefoundry/ir/hir/tensor/index_copy.py
src/tilefoundry/ir/hir/tensor/index_select.py
src/tilefoundry/ir/hir/tensor/insert_slice.py
src/tilefoundry/ir/hir/tensor/quant.py
src/tilefoundry/ir/hir/tensor/rank.py
src/tilefoundry/ir/hir/tensor/reduce.py
src/tilefoundry/ir/hir/tensor/repeat_interleave.py
src/tilefoundry/ir/hir/tensor/reshape.py
src/tilefoundry/ir/hir/tensor/shape_of.py
src/tilefoundry/ir/hir/tensor/slice.py
src/tilefoundry/ir/hir/tensor/split.py
src/tilefoundry/ir/hir/tensor/stack.py
src/tilefoundry/ir/hir/tensor/topk.py
src/tilefoundry/ir/hir/tensor/transpose.py
src/tilefoundry/ir/hir/tensor/tuple_get_item.py
src/tilefoundry/ir/hir/tensor/where.py
src/tilefoundry/ir/hir/tensor/zeros.py
src/tilefoundry/ir/pattern/__init__.py
src/tilefoundry/ir/pattern/constraint.py
src/tilefoundry/ir/pattern/match.py
src/tilefoundry/ir/pattern/pattern.py
src/tilefoundry/ir/pattern/predicates.py
src/tilefoundry/ir/pattern/utils.py
src/tilefoundry/ir/tir/__init__.py
src/tilefoundry/ir/tir/abort.py
src/tilefoundry/ir/tir/arange.py
src/tilefoundry/ir/tir/arith.py
src/tilefoundry/ir/tir/async_copy.py
src/tilefoundry/ir/tir/cast.py
src/tilefoundry/ir/tir/clamp.py
src/tilefoundry/ir/tir/dot.py
src/tilefoundry/ir/tir/intrinsic.py
src/tilefoundry/ir/tir/launch.py
src/tilefoundry/ir/tir/prim_function.py
src/tilefoundry/ir/tir/reduce.py
src/tilefoundry/ir/tir/shape.py
src/tilefoundry/ir/tir/stmt.py
src/tilefoundry/ir/tir/stmts.py
src/tilefoundry/ir/tir/symbol_ref.py
src/tilefoundry/ir/tir/sync.py
src/tilefoundry/ir/tir/where.py
src/tilefoundry/ir/tir/memory/__init__.py
src/tilefoundry/ir/tir/memory/alloc_tensor.py
src/tilefoundry/ir/tir/memory/copy.py
src/tilefoundry/ir/tir/memory/fill.py
src/tilefoundry/ir/tir/memory/memory_span.py
src/tilefoundry/ir/tir/memory/ptr_of.py
src/tilefoundry/ir/tir/memory/tensor_view.py
src/tilefoundry/ir/tir/nn/__init__.py
src/tilefoundry/ir/tir/nn/relu.py
src/tilefoundry/ir/types/__init__.py
src/tilefoundry/ir/types/callable_type.py
src/tilefoundry/ir/types/dim.py
src/tilefoundry/ir/types/dim_typeinfer.py
src/tilefoundry/ir/types/dtype.py
src/tilefoundry/ir/types/int_tuple.py
src/tilefoundry/ir/types/layout.py
src/tilefoundry/ir/types/layout_algebra.py
src/tilefoundry/ir/types/mesh.py
src/tilefoundry/ir/types/placement.py
src/tilefoundry/ir/types/pointer.py
src/tilefoundry/ir/types/shard_layout.py
src/tilefoundry/ir/types/storage.py
src/tilefoundry/ir/types/stride.py
src/tilefoundry/ir/types/substitute.py
src/tilefoundry/ir/types/swizzle_layout.py
src/tilefoundry/ir/types/tensor_type.py
src/tilefoundry/ir/types/utils.py
src/tilefoundry/orchestrator/causal_lm/generation.py
src/tilefoundry/orchestrator/causal_lm/run.py
src/tilefoundry/parser/__init__.py
src/tilefoundry/parser/ast_pattern.py
src/tilefoundry/parser/grammar_render.py
src/tilefoundry/parser/parser_visitor.py
src/tilefoundry/parser/pattern_nodes.py
src/tilefoundry/parser/spec.py
src/tilefoundry/passes/__init__.py
src/tilefoundry/passes/pass_base.py
src/tilefoundry/passes/pass_manager.py
src/tilefoundry/passes/transforms/__init__.py
src/tilefoundry/passes/transforms/convert_hir_to_tir.py
src/tilefoundry/runtime/__init__.py
src/tilefoundry/runtime/decorator.py
src/tilefoundry/runtime/function.py
src/tilefoundry/runtime/loader.py
src/tilefoundry/runtime/measure.py
src/tilefoundry/runtime/module.py
src/tilefoundry/runtime/resource.py
src/tilefoundry/runtime/tensor.py
src/tilefoundry/runtime/include/tilefoundry/runtime/cpu/runtime.h
src/tilefoundry/schedule/__init__.py
src/tilefoundry/schedule/_reporting.py
src/tilefoundry/schedule/candidates.py
src/tilefoundry/schedule/facts.py
src/tilefoundry/schedule/finalize.py
src/tilefoundry/target/__init__.py
src/tilefoundry/target/base.py
src/tilefoundry/target/facts.py
src/tilefoundry/target/services.py
src/tilefoundry/target/cpu/__init__.py
src/tilefoundry/target/cpu/target.py
src/tilefoundry/target/hardware/__init__.py
src/tilefoundry/target/hardware/envelope.py
src/tilefoundry/target/hardware/schema.py
src/tilefoundry/target/hardware/spec.py
src/tilefoundry/utils/__init__.py
src/tilefoundry/utils/isl_utils.py
src/tilefoundry/utils/lazy.py
src/tilefoundry/utils/markdown.py
src/tilefoundry/utils/python_source.py
src/tilefoundry/utils/spec_ref.py
src/tilefoundry/utils/units.py
src/tilefoundry/visitor_registry/__init__.py
src/tilefoundry/visitor_registry/access_relation.py
src/tilefoundry/visitor_registry/buffer_alias.py
src/tilefoundry/visitor_registry/contexts.py
src/tilefoundry/visitor_registry/cost_utils.py
src/tilefoundry/visitor_registry/instruction.py
src/tilefoundry/visitor_registry/op_cost.py
src/tilefoundry/visitor_registry/registries.py
src/tilefoundry/visitor_registry/shard_propagate.py
src/tilefoundry/visitor_registry/typeinfer.py
src/tilefoundry/visitor_registry/valuation.py
src/tilefoundry/visitor_registry/verify.py
src/tilefoundry/visitor_registry/visitors.py
src/tilefoundry/visitor_registry/candidates/__init__.py
src/tilefoundry/visitor_registry/candidates/common.py
targets/apple/LICENSE
targets/apple/README.md
targets/apple/pyproject.toml
targets/apple/setup.py
targets/apple/tilefoundry_apple/__init__.py
targets/apple/tilefoundry_apple/amx/__init__.py
targets/apple/tilefoundry_apple/amx/docs/spec/target.md
targets/apple/tilefoundry_apple/amx/docs/spec/tir.md
targets/apple/tilefoundry_apple/amx/include/tilefoundry/runtime/amx/instructions.h
targets/apple/tilefoundry_apple/amx/ir/__init__.py
targets/apple/tilefoundry_apple/amx/ir/tir/__init__.py
targets/apple/tilefoundry_apple/amx/ir/tir/instructions.py
targets/apple/tilefoundry_apple/amx/target/__init__.py
targets/apple/tilefoundry_apple/amx/target/architecture.py
targets/apple/tilefoundry_apple/amx/target/device.py
targets/apple/tilefoundry_apple/amx/target/facts.py
targets/apple/tilefoundry_apple/amx/target/spec.py
targets/apple/tilefoundry_apple/amx/target/target.py
targets/apple/tilefoundry_apple/amx/target/hardware/__init__.py
targets/apple/tilefoundry_apple/amx/target/hardware/apple_amx.toml
targets/apple/tilefoundry_apple/amx/target/hardware/apple_m2_pro.toml
targets/apple/tilefoundry_apple/amx/visitor_registry/__init__.py
targets/apple/tilefoundry_apple/amx/visitor_registry/candidates.py
targets/nvidia/LICENSE
targets/nvidia/README.md
targets/nvidia/pyproject.toml
targets/nvidia/setup.py
targets/nvidia/tilefoundry_nvidia/__init__.py
targets/nvidia/tilefoundry_nvidia/cuda/__init__.py
targets/nvidia/tilefoundry_nvidia/cuda/codegen/__init__.py
targets/nvidia/tilefoundry_nvidia/cuda/codegen/abi.py
targets/nvidia/tilefoundry_nvidia/cuda/codegen/context.py
targets/nvidia/tilefoundry_nvidia/cuda/codegen/emit.py
targets/nvidia/tilefoundry_nvidia/cuda/codegen/host_launch.py
targets/nvidia/tilefoundry_nvidia/cuda/codegen/module.py
targets/nvidia/tilefoundry_nvidia/cuda/codegen/hir/__init__.py
targets/nvidia/tilefoundry_nvidia/cuda/codegen/hir/function.py
targets/nvidia/tilefoundry_nvidia/cuda/codegen/include/tilefoundry/runtime/cuda/runtime.cuh
targets/nvidia/tilefoundry_nvidia/cuda/codegen/include/tilefoundry/runtime/cuda/layout/cute_ext.cuh
targets/nvidia/tilefoundry_nvidia/cuda/codegen/include/tilefoundry/runtime/cuda/layout/mesh.cuh
targets/nvidia/tilefoundry_nvidia/cuda/codegen/include/tilefoundry/runtime/cuda/layout/shard_layout.cuh
targets/nvidia/tilefoundry_nvidia/cuda/codegen/include/tilefoundry/runtime/cuda/ops/copy.cuh
targets/nvidia/tilefoundry_nvidia/cuda/codegen/include/tilefoundry/runtime/cuda/ops/copy_async_bulk.cuh
targets/nvidia/tilefoundry_nvidia/cuda/codegen/include/tilefoundry/runtime/cuda/ops/detail.cuh
targets/nvidia/tilefoundry_nvidia/cuda/codegen/include/tilefoundry/runtime/cuda/ops/dot.cuh
targets/nvidia/tilefoundry_nvidia/cuda/codegen/include/tilefoundry/runtime/cuda/ops/elementwise.cuh
targets/nvidia/tilefoundry_nvidia/cuda/codegen/include/tilefoundry/runtime/cuda/ops/ldmatrix.cuh
targets/nvidia/tilefoundry_nvidia/cuda/codegen/include/tilefoundry/runtime/cuda/ops/mma.cuh
targets/nvidia/tilefoundry_nvidia/cuda/codegen/include/tilefoundry/runtime/cuda/ops/reduce.cuh
targets/nvidia/tilefoundry_nvidia/cuda/codegen/include/tilefoundry/runtime/cuda/ops/sync.cuh
targets/nvidia/tilefoundry_nvidia/cuda/codegen/include/tilefoundry/runtime/cuda/ops/copy/copy_impl.h
targets/nvidia/tilefoundry_nvidia/cuda/codegen/include/tilefoundry/runtime/cuda/ops/copy_async_bulk/copy_async_bulk_impl.h
targets/nvidia/tilefoundry_nvidia/cuda/codegen/include/tilefoundry/runtime/cuda/ops/dot/dot_impl.h
targets/nvidia/tilefoundry_nvidia/cuda/codegen/include/tilefoundry/runtime/cuda/ops/elementwise/elementwise_impl.h
targets/nvidia/tilefoundry_nvidia/cuda/codegen/include/tilefoundry/runtime/cuda/ops/ldmatrix/ldmatrix_impl.h
targets/nvidia/tilefoundry_nvidia/cuda/codegen/include/tilefoundry/runtime/cuda/ops/mma/mma_impl.h
targets/nvidia/tilefoundry_nvidia/cuda/codegen/include/tilefoundry/runtime/cuda/ops/reduce/reduce_common_impl.h
targets/nvidia/tilefoundry_nvidia/cuda/codegen/include/tilefoundry/runtime/cuda/ops/reduce/reduce_cross_warp_impl.h
targets/nvidia/tilefoundry_nvidia/cuda/codegen/include/tilefoundry/runtime/cuda/ops/reduce/reduce_intra_cta_impl.h
targets/nvidia/tilefoundry_nvidia/cuda/codegen/include/tilefoundry/runtime/cuda/ops/reduce/reduce_intra_warp_impl.h
targets/nvidia/tilefoundry_nvidia/cuda/codegen/include/tilefoundry/runtime/cuda/ops/reduce/reduce_plain_impl.h
targets/nvidia/tilefoundry_nvidia/cuda/codegen/include/tilefoundry/runtime/cuda/ops/sync/sync_impl.h
targets/nvidia/tilefoundry_nvidia/cuda/codegen/include/tilefoundry/runtime/cuda/primitive/binary.h
targets/nvidia/tilefoundry_nvidia/cuda/codegen/include/tilefoundry/runtime/cuda/primitive/unary.h
targets/nvidia/tilefoundry_nvidia/cuda/codegen/include/tilefoundry/runtime/cuda/tensor_view/shard_tensor.cuh
targets/nvidia/tilefoundry_nvidia/cuda/codegen/include/tilefoundry/runtime/cuda/utility/warp.cuh
targets/nvidia/tilefoundry_nvidia/cuda/codegen/templates/__init__.py
targets/nvidia/tilefoundry_nvidia/cuda/codegen/templates/cuda_preamble.cu.j2
targets/nvidia/tilefoundry_nvidia/cuda/codegen/tir/__init__.py
targets/nvidia/tilefoundry_nvidia/cuda/codegen/tir/arith.py
targets/nvidia/tilefoundry_nvidia/cuda/codegen/tir/async_copy.py
targets/nvidia/tilefoundry_nvidia/cuda/codegen/tir/clamp.py
targets/nvidia/tilefoundry_nvidia/cuda/codegen/tir/cute_layout.py
targets/nvidia/tilefoundry_nvidia/cuda/codegen/tir/dot.py
targets/nvidia/tilefoundry_nvidia/cuda/codegen/tir/mbarrier.py
targets/nvidia/tilefoundry_nvidia/cuda/codegen/tir/prim_function.py
targets/nvidia/tilefoundry_nvidia/cuda/codegen/tir/reduce.py
targets/nvidia/tilefoundry_nvidia/cuda/codegen/tir/sync.py
targets/nvidia/tilefoundry_nvidia/cuda/codegen/tir/tuple_get_item.py
targets/nvidia/tilefoundry_nvidia/cuda/codegen/tir/memory/__init__.py
targets/nvidia/tilefoundry_nvidia/cuda/codegen/tir/memory/alloc_tensor.py
targets/nvidia/tilefoundry_nvidia/cuda/codegen/tir/memory/copy.py
targets/nvidia/tilefoundry_nvidia/cuda/codegen/tir/memory/copy_async_bulk.py
targets/nvidia/tilefoundry_nvidia/cuda/codegen/tir/memory/copy_async_tensor.py
targets/nvidia/tilefoundry_nvidia/cuda/codegen/tir/memory/copy_reduce_async_tensor.py
targets/nvidia/tilefoundry_nvidia/cuda/codegen/tir/memory/fill.py
targets/nvidia/tilefoundry_nvidia/cuda/codegen/tir/memory/ldmatrix.py
targets/nvidia/tilefoundry_nvidia/cuda/codegen/tir/memory/ptr_of.py
targets/nvidia/tilefoundry_nvidia/cuda/codegen/tir/memory/stmatrix.py
targets/nvidia/tilefoundry_nvidia/cuda/codegen/tir/memory/tensor_view.py
targets/nvidia/tilefoundry_nvidia/cuda/codegen/tir/nn/__init__.py
targets/nvidia/tilefoundry_nvidia/cuda/codegen/tir/nn/mma.py
targets/nvidia/tilefoundry_nvidia/cuda/codegen/tir/nn/relu.py
targets/nvidia/tilefoundry_nvidia/cuda/codegen/tir/stmts/__init__.py
targets/nvidia/tilefoundry_nvidia/cuda/codegen/tir/stmts/mesh_scope.py
targets/nvidia/tilefoundry_nvidia/cuda/docs/spec/cli.md
targets/nvidia/tilefoundry_nvidia/cuda/docs/spec/codegen.md
targets/nvidia/tilefoundry_nvidia/cuda/docs/spec/hir.md
targets/nvidia/tilefoundry_nvidia/cuda/docs/spec/passes.md
targets/nvidia/tilefoundry_nvidia/cuda/docs/spec/runtime.md
targets/nvidia/tilefoundry_nvidia/cuda/docs/spec/target.md
targets/nvidia/tilefoundry_nvidia/cuda/docs/spec/tir.md
targets/nvidia/tilefoundry_nvidia/cuda/ir/__init__.py
targets/nvidia/tilefoundry_nvidia/cuda/ir/hir/__init__.py
targets/nvidia/tilefoundry_nvidia/cuda/ir/hir/nn/__init__.py
targets/nvidia/tilefoundry_nvidia/cuda/ir/hir/nn/matmul.py
targets/nvidia/tilefoundry_nvidia/cuda/ir/tir/__init__.py
targets/nvidia/tilefoundry_nvidia/cuda/ir/tir/launch.py
targets/nvidia/tilefoundry_nvidia/cuda/ir/tir/memory/__init__.py
targets/nvidia/tilefoundry_nvidia/cuda/ir/tir/memory/copy_async_bulk.py
targets/nvidia/tilefoundry_nvidia/cuda/ir/tir/memory/copy_async_tensor.py
targets/nvidia/tilefoundry_nvidia/cuda/ir/tir/memory/copy_reduce_async_tensor.py
targets/nvidia/tilefoundry_nvidia/cuda/ir/tir/memory/ldmatrix.py
targets/nvidia/tilefoundry_nvidia/cuda/ir/tir/memory/stmatrix.py
targets/nvidia/tilefoundry_nvidia/cuda/ir/tir/nn/__init__.py
targets/nvidia/tilefoundry_nvidia/cuda/ir/tir/nn/mma.py
targets/nvidia/tilefoundry_nvidia/cuda/ir/tir/nn/mma_atom.py
targets/nvidia/tilefoundry_nvidia/cuda/ir/tir/nn/sm80_mma.py
targets/nvidia/tilefoundry_nvidia/cuda/ir/tir/nn/sm89_mma.py
targets/nvidia/tilefoundry_nvidia/cuda/ir/tir/nn/wgmma.py
targets/nvidia/tilefoundry_nvidia/cuda/ir/tir/sync/__init__.py
targets/nvidia/tilefoundry_nvidia/cuda/ir/tir/sync/mbarrier.py
targets/nvidia/tilefoundry_nvidia/cuda/models/catalog.json
targets/nvidia/tilefoundry_nvidia/cuda/models/deepseek_v4_flash/config.json
targets/nvidia/tilefoundry_nvidia/cuda/models/deepseek_v4_flash/model.py
targets/nvidia/tilefoundry_nvidia/cuda/models/gemma2_2b/config.json
targets/nvidia/tilefoundry_nvidia/cuda/models/gemma2_2b/hf_alias.py
targets/nvidia/tilefoundry_nvidia/cuda/models/gemma2_2b/model.py
targets/nvidia/tilefoundry_nvidia/cuda/models/kimi_linear_48b_a3b/config.json
targets/nvidia/tilefoundry_nvidia/cuda/models/kimi_linear_48b_a3b/model.py
targets/nvidia/tilefoundry_nvidia/cuda/models/minicpm3_4b/config.json
targets/nvidia/tilefoundry_nvidia/cuda/models/minicpm3_4b/hf_alias.py
targets/nvidia/tilefoundry_nvidia/cuda/models/minicpm3_4b/model.py
targets/nvidia/tilefoundry_nvidia/cuda/models/qwen2_5_1_5b/config.json
targets/nvidia/tilefoundry_nvidia/cuda/models/qwen2_5_1_5b/hf_alias.py
targets/nvidia/tilefoundry_nvidia/cuda/models/qwen2_5_1_5b/model.py
targets/nvidia/tilefoundry_nvidia/cuda/models/qwen3_1_7b/config.json
targets/nvidia/tilefoundry_nvidia/cuda/models/qwen3_1_7b/hf_alias.py
targets/nvidia/tilefoundry_nvidia/cuda/models/qwen3_1_7b/model.py
targets/nvidia/tilefoundry_nvidia/cuda/models/qwen3_5_35b_a3b/config.json
targets/nvidia/tilefoundry_nvidia/cuda/models/qwen3_5_35b_a3b/hf_alias.py
targets/nvidia/tilefoundry_nvidia/cuda/models/qwen3_5_35b_a3b/model.py
targets/nvidia/tilefoundry_nvidia/cuda/passes/__init__.py
targets/nvidia/tilefoundry_nvidia/cuda/passes/transforms/__init__.py
targets/nvidia/tilefoundry_nvidia/cuda/passes/transforms/host_entry.py
targets/nvidia/tilefoundry_nvidia/cuda/target/__init__.py
targets/nvidia/tilefoundry_nvidia/cuda/target/architecture.py
targets/nvidia/tilefoundry_nvidia/cuda/target/device.py
targets/nvidia/tilefoundry_nvidia/cuda/target/facts.py
targets/nvidia/tilefoundry_nvidia/cuda/target/spec.py
targets/nvidia/tilefoundry_nvidia/cuda/target/target.py
targets/nvidia/tilefoundry_nvidia/cuda/target/hardware/__init__.py
targets/nvidia/tilefoundry_nvidia/cuda/target/hardware/nvidia_b200_sxm.toml
targets/nvidia/tilefoundry_nvidia/cuda/target/hardware/nvidia_h200_sxm.toml
targets/nvidia/tilefoundry_nvidia/cuda/target/hardware/nvidia_rtx_6000_ada.toml
targets/nvidia/tilefoundry_nvidia/cuda/target/hardware/nvidia_sm100.toml
targets/nvidia/tilefoundry_nvidia/cuda/target/hardware/nvidia_sm89.toml
targets/nvidia/tilefoundry_nvidia/cuda/target/hardware/nvidia_sm90.toml
targets/nvidia/tilefoundry_nvidia/cuda/visitor_registry/__init__.py
targets/nvidia/tilefoundry_nvidia/cuda/visitor_registry/candidates.py
tests/__init__.py
tests/conftest.py
tests/apple/__init__.py
tests/apple/amx/__init__.py
tests/apple/amx/cli/__init__.py
tests/apple/amx/cli/test_cli.py
tests/apple/amx/fixtures/shapes/matmul_programs.py
tests/apple/amx/installed/__init__.py
tests/apple/amx/installed/conftest.py
tests/apple/amx/installed/smoke_spec.py
tests/apple/amx/installed/smoke_target_cli.py
tests/apple/amx/parser/__init__.py
tests/apple/amx/parser/test_functions.py
tests/apple/amx/schedule/__init__.py
tests/apple/amx/schedule/test_fixtures.py
tests/apple/amx/target/__init__.py
tests/apple/amx/target/test_amx_target.py
tests/apple/amx/target/test_hardware_resources.py
tests/apple/amx/target/test_target.py
tests/apple/amx/target/test_target_facts.py
tests/core/__init__.py
tests/core/_source.py
tests/core/analysis/__init__.py
tests/core/analysis/test_allocation.py
tests/core/analysis/test_analysis_invariants.py
tests/core/analysis/test_isl_utility.py
tests/core/analysis/test_mesh_region_cost.py
tests/core/analysis/test_shard_propagate.py
tests/core/cli/__init__.py
tests/core/cli/_check.py
tests/core/cli/_targets.py
tests/core/cli/test_cli.py
tests/core/cli/test_cli_check.py
tests/core/codegen/__init__.py
tests/core/codegen/test_linkable.py
tests/core/dsl/__init__.py
tests/core/dsl/test_dsl_surface.py
tests/core/dsl/test_module_context.py
tests/core/dsl/test_module_decorator.py
tests/core/dsl/test_tiled_mlp.py
tests/core/dump/__init__.py
tests/core/dump/test_dump.py
tests/core/evaluator/__init__.py
tests/core/evaluator/eval_utils.py
tests/core/evaluator/test_eval_core.py
tests/core/fixtures/__init__.py
tests/core/fixtures/meshes.py
tests/core/fixtures/diagnostics/__init__.py
tests/core/fixtures/diagnostics/coarse_rmem.py
tests/core/fixtures/diagnostics/region_rebind.py
tests/core/fixtures/diagnostics/region_tuple_rebind.py
tests/core/fixtures/diagnostics/value_escapes.py
tests/core/fixtures/inspection/__init__.py
tests/core/fixtures/logical/__init__.py
tests/core/fixtures/logical/callee_dim.py
tests/core/fixtures/logical/handwritten_twin.py
tests/core/fixtures/logical/mislabelled_twin.py
tests/core/fixtures/logical/orchestrated_twin.py
tests/core/fixtures/placed/__init__.py
tests/core/fixtures/placed/fused_twin.py
tests/core/fixtures/placed/gqa_decode.py
tests/core/fixtures/placed/nested_twin.py
tests/core/fixtures/placed/square_cpu.py
tests/core/fixtures/placed/square_cpu_runtime.py
tests/core/fixtures/placed/square_twin.py
tests/core/fixtures/placed/weighted_twin.py
tests/core/fixtures/shapes/__init__.py
tests/core/fixtures/shapes/matmul_programs.py
tests/core/fixtures/shapes/tile_window_syntax.py
tests/core/fixtures/tir/__init__.py
tests/core/fixtures/tir/layouts.py
tests/core/inspection/__init__.py
tests/core/inspection/_tir_roundtrip.py
tests/core/inspection/test_module_tree_roundtrip.py
tests/core/inspection/test_python_printer.py
tests/core/inspection/test_roundtrip.py
tests/core/inspection/test_specialization_print.py
tests/core/inspection/test_tir_roundtrip.py
tests/core/installed/__init__.py
tests/core/installed/_analyze.py
tests/core/installed/_spec.py
tests/core/installed/_targets.py
tests/core/installed/conftest.py
tests/core/installed/smoke_analyze.py
tests/core/installed/smoke_check.py
tests/core/installed/smoke_shipped.py
tests/core/installed/smoke_spec.py
tests/core/installed/smoke_target_cli.py
tests/core/installed/smoke_tutorial.py
tests/core/installed/smoke_target/__init__.py
tests/core/installed/smoke_target/vendor_npu/__init__.py
tests/core/integration/__init__.py
tests/core/integration/test_host_launch.py
tests/core/ir/__init__.py
tests/core/ir/test_copy_reduce_async_tensor.py
tests/core/ir/test_dim_var_envelope.py
tests/core/ir/test_function_call_typeinfer.py
tests/core/ir/test_loop_region_dynamic_extent.py
tests/core/ir/test_loop_region_range_nested.py
tests/core/ir/test_shape_of.py
tests/core/ir/test_shard_layout_local_shape.py
tests/core/ir/test_simplify_dim.py
tests/core/ir/test_verify_letstmt.py
tests/core/ir/test_visitor.py
tests/core/ir/core/__init__.py
tests/core/ir/core/test_dim_substitution.py
tests/core/ir/core/test_gqa_online.py
tests/core/ir/core/test_metadata.py
tests/core/ir/core/test_param_def.py
tests/core/ir/core/test_pattern.py
tests/core/ir/core/test_register_alias.py
tests/core/ir/core/test_specialize.py
tests/core/ir/core/test_typeinfer_discipline.py
tests/core/ir/pattern/__init__.py
tests/core/ir/pattern/test_mesh_pattern.py
tests/core/ir/types/__init__.py
tests/core/ir/types/test_dtype.py
tests/core/ir/types/test_local_layout.py
tests/core/ir/types/test_mesh.py
tests/core/ir/types/test_shard_layout.py
tests/core/ir/types/test_storage.py
tests/core/ir/types/test_tensor_type.py
tests/core/models/__init__.py
tests/core/models/decode_oracle.py
tests/core/models/dense_decode.py
tests/core/ops/__init__.py
tests/core/ops/ir/__init__.py
tests/core/ops/ir/cost_utils.py
tests/core/ops/ir/test_arange.py
tests/core/ops/ir/test_argmax.py
tests/core/ops/ir/test_binary.py
tests/core/ops/ir/test_bitcast.py
tests/core/ops/ir/test_cache_update.py
tests/core/ops/ir/test_cast.py
tests/core/ops/ir/test_clamp.py
tests/core/ops/ir/test_concat.py
tests/core/ops/ir/test_conv2d.py
tests/core/ops/ir/test_layer_norm.py
tests/core/ops/ir/test_matmul.py
tests/core/ops/ir/test_quant.py
tests/core/ops/ir/test_relu.py
tests/core/ops/ir/test_repeat_interleave.py
tests/core/ops/ir/test_reshape.py
tests/core/ops/ir/test_reshard.py
tests/core/ops/ir/test_rms_norm.py
tests/core/ops/ir/test_rope.py
tests/core/ops/ir/test_shape_metadata.py
tests/core/ops/ir/test_sigmoid.py
tests/core/ops/ir/test_silu.py
tests/core/ops/ir/test_slice.py
tests/core/ops/ir/test_softmax.py
tests/core/ops/ir/test_softplus.py
tests/core/ops/ir/test_split.py
tests/core/ops/ir/test_stack.py
tests/core/ops/ir/test_tanh.py
tests/core/ops/ir/test_topk.py
tests/core/ops/ir/test_transpose.py
tests/core/ops/ir/test_unary.py
tests/core/ops/ir/test_where.py
tests/core/ops/ir/typeinfer_utils.py
tests/core/ops/tir/__init__.py
tests/core/parser/__init__.py
tests/core/parser/_fixtures.py
tests/core/parser/test_calls.py
tests/core/parser/test_functions.py
tests/core/parser/test_mesh_visibility.py
tests/core/parser/test_roundtrip.py
tests/core/parser/test_slices.py
tests/core/passes/__init__.py
tests/core/passes/test_pass_manager.py
tests/core/runtime/__init__.py
tests/core/runtime/resource/__init__.py
tests/core/runtime/resource/test_resource_device.py
tests/core/schedule/__init__.py
tests/core/schedule/_fixtures.py
tests/core/schedule/test_fixtures.py
tests/core/scripts/__init__.py
tests/core/scripts/test_comment_hygiene_lint.py
tests/core/scripts/test_no_machine_paths_lint.py
tests/core/scripts/test_spec_refs_lint.py
tests/core/target/__init__.py
tests/core/target/_hardware.py
tests/core/target/_instructions.py
tests/core/target/test_hardware_resources.py
tests/core/target/test_target.py
tests/core/target/test_target_facts.py
tests/core/visitor_registry/__init__.py
tests/core/visitor_registry/test_visitor_registry.py
tests/nvidia/__init__.py
tests/nvidia/conftest.py
tests/nvidia/cuda/__init__.py
tests/nvidia/cuda/analysis/__init__.py
tests/nvidia/cuda/analysis/test_allocation.py
tests/nvidia/cuda/analysis/test_analysis_families.py
tests/nvidia/cuda/analysis/test_analyze_at_a_size.py
tests/nvidia/cuda/analysis/test_analyze_by_hand.py
tests/nvidia/cuda/analysis/test_analyze_composition.py
tests/nvidia/cuda/analysis/test_analyze_cross_module.py
tests/nvidia/cuda/analysis/test_isl_utility.py
tests/nvidia/cuda/analysis/test_mesh_region_cost.py
tests/nvidia/cuda/analysis/test_render_golden.py
tests/nvidia/cuda/analysis/test_shard_propagate.py
tests/nvidia/cuda/cli/__init__.py
tests/nvidia/cuda/cli/test_cli.py
tests/nvidia/cuda/cli/test_cli_check.py
tests/nvidia/cuda/codegen/__init__.py
tests/nvidia/cuda/codegen/test_device_dispatch.py
tests/nvidia/cuda/codegen/test_host_multi_launch.py
tests/nvidia/cuda/codegen/test_linkable.py
tests/nvidia/cuda/codegen/test_reduce_tag_table.py
tests/nvidia/cuda/codegen/test_shard_layout_value.py
tests/nvidia/cuda/codegen/test_staged_ring.py
tests/nvidia/cuda/codegen/test_stmatrix.py
tests/nvidia/cuda/codegen/test_submodule_topology.py
tests/nvidia/cuda/dsl/__init__.py
tests/nvidia/cuda/dsl/test_module_context.py
tests/nvidia/cuda/dsl/test_module_decorator.py
tests/nvidia/cuda/evaluator/__init__.py
tests/nvidia/cuda/evaluator/test_eval_core.py
tests/nvidia/cuda/fixtures/diagnostics/dynamic_trip_count.py
tests/nvidia/cuda/fixtures/diagnostics/layout_crossing_axes.py
tests/nvidia/cuda/fixtures/diagnostics/tuple_projection_diagnostic.py
tests/nvidia/cuda/fixtures/diagnostics/unscoped_call_loop.py
tests/nvidia/cuda/fixtures/inspection/type_printer_sugar.analyzed.txt
tests/nvidia/cuda/fixtures/inspection/type_printer_sugar.printed.txt
tests/nvidia/cuda/fixtures/inspection/type_printer_sugar.py
tests/nvidia/cuda/fixtures/logical/authored_constraint.py
tests/nvidia/cuda/fixtures/logical/gqa_static.py
tests/nvidia/cuda/fixtures/logical/hir_composition.py
tests/nvidia/cuda/fixtures/logical/matmul_rms_norm.py
tests/nvidia/cuda/fixtures/logical/module_context.py
tests/nvidia/cuda/fixtures/placed/child_matmul_target.py
tests/nvidia/cuda/fixtures/placed/cyclic_split_weight.py
tests/nvidia/cuda/fixtures/placed/data_started_window.py
tests/nvidia/cuda/fixtures/placed/derived_prefill.py
tests/nvidia/cuda/fixtures/placed/flash_split_k_decode.py
tests/nvidia/cuda/fixtures/placed/fused_boundary.py
tests/nvidia/cuda/fixtures/placed/gemm_schedules.py
tests/nvidia/cuda/fixtures/placed/gpu_placed_rows.py
tests/nvidia/cuda/fixtures/placed/hand_checked.py
tests/nvidia/cuda/fixtures/placed/leaf_weights.py
tests/nvidia/cuda/fixtures/placed/mesh_pricing.py
tests/nvidia/cuda/fixtures/placed/mesh_slice_start.py
tests/nvidia/cuda/fixtures/placed/mha_decode_paged.py
tests/nvidia/cuda/fixtures/placed/moe_mega_kernel.py
tests/nvidia/cuda/fixtures/placed/performance_findings.py
tests/nvidia/cuda/fixtures/placed/persistent_gemm_flat.py
tests/nvidia/cuda/fixtures/placed/persistent_gemm_tiled.py
tests/nvidia/cuda/fixtures/placed/prefill_decode_attention.py
tests/nvidia/cuda/fixtures/placed/qwen3_1_7b_pd.py
tests/nvidia/cuda/fixtures/placed/region_boundaries.py
tests/nvidia/cuda/fixtures/placed/rmsnorm.py
tests/nvidia/cuda/fixtures/placed/rmsnorm_quant_seq2.py
tests/nvidia/cuda/fixtures/placed/rmsnorm_seq2.py
tests/nvidia/cuda/fixtures/placed/specialize_through_call.py
tests/nvidia/cuda/fixtures/placed/square_cuda.py
tests/nvidia/cuda/fixtures/placed/symbolic_offset.py
tests/nvidia/cuda/fixtures/placed/tiny_tp_decoder.py
tests/nvidia/cuda/fixtures/placed/tp_all_to_all.py
tests/nvidia/cuda/fixtures/placed/two_dimvar_reshape.py
tests/nvidia/cuda/fixtures/scaffold/hir_layers.py
tests/nvidia/cuda/fixtures/scaffold/hir_moe.py
tests/nvidia/cuda/fixtures/scaffold/tir_dispatch.py
tests/nvidia/cuda/fixtures/scaffold/tir_launches.py
tests/nvidia/cuda/fixtures/schedule/Wgmma.facts.txt
tests/nvidia/cuda/fixtures/schedule/__init__.py
tests/nvidia/cuda/fixtures/schedule/tiled_mma.facts.txt
tests/nvidia/cuda/fixtures/schedule/hir/bulk_reduce_store.py
tests/nvidia/cuda/fixtures/schedule/hir/captured_insert_update.py
tests/nvidia/cuda/fixtures/schedule/hir/child_weight.py
tests/nvidia/cuda/fixtures/schedule/hir/cta_submesh_thread_scope.py
tests/nvidia/cuda/fixtures/schedule/hir/duplicate_output_storage.py
tests/nvidia/cuda/fixtures/schedule/hir/finalize_footprint_mesh_offset.py
tests/nvidia/cuda/fixtures/schedule/hir/fp8_block_scaled_gemm.py
tests/nvidia/cuda/fixtures/schedule/hir/gemm_8192x17408x5120_register_store.py
tests/nvidia/cuda/fixtures/schedule/hir/gemm_8192x17408x5120_tma_store.analyzed.txt
tests/nvidia/cuda/fixtures/schedule/hir/gemm_8192x17408x5120_tma_store.py
tests/nvidia/cuda/fixtures/schedule/hir/inplace_output_update.py
tests/nvidia/cuda/fixtures/schedule/hir/loop_bound_from_outer_induction.py
tests/nvidia/cuda/fixtures/schedule/hir/loop_carry_from_param.py
tests/nvidia/cuda/fixtures/schedule/hir/loop_carry_rebind.py
tests/nvidia/cuda/fixtures/schedule/hir/loop_carry_window.py
tests/nvidia/cuda/fixtures/schedule/hir/loop_outputs.py
tests/nvidia/cuda/fixtures/schedule/hir/loop_variable_rebound.py
tests/nvidia/cuda/fixtures/schedule/hir/mesh_capture_outside.py
tests/nvidia/cuda/fixtures/schedule/hir/mesh_views.py
tests/nvidia/cuda/fixtures/schedule/hir/mesh_zeros_submesh.py
tests/nvidia/cuda/fixtures/schedule/hir/module_instances.py
tests/nvidia/cuda/fixtures/schedule/hir/persistent_tile_union_count.py
tests/nvidia/cuda/fixtures/schedule/hir/register_arange.py
tests/nvidia/cuda/fixtures/schedule/hir/register_full_like.py
tests/nvidia/cuda/fixtures/schedule/hir/register_index_window.py
tests/nvidia/cuda/fixtures/schedule/hir/register_index_window_offset.py
tests/nvidia/cuda/fixtures/schedule/hir/reshard_views.py
tests/nvidia/cuda/fixtures/schedule/hir/scalar_binary.py
tests/nvidia/cuda/fixtures/schedule/hir/scalar_ceildiv_gate.py
tests/nvidia/cuda/fixtures/schedule/hir/sm80_mma_ldmatrix.py
tests/nvidia/cuda/fixtures/schedule/hir/sm89_e4m3_gemm.py
tests/nvidia/cuda/fixtures/schedule/hir/smem_padded_stages.py
tests/nvidia/cuda/fixtures/schedule/hir/sparse_decode.py
tests/nvidia/cuda/fixtures/schedule/hir/staged_dynamic_inner.py
tests/nvidia/cuda/fixtures/schedule/hir/staged_nested.py
tests/nvidia/cuda/fixtures/schedule/hir/strided_return_window.py
tests/nvidia/cuda/fixtures/schedule/hir/submesh_slice_in_sibling.py
tests/nvidia/cuda/fixtures/schedule/hir/view_visit_memo.py
tests/nvidia/cuda/fixtures/schedule/hir/wgmma_a_k_major.py
tests/nvidia/cuda/fixtures/schedule/hir/wgmma_a_mn_major.py
tests/nvidia/cuda/fixtures/schedule/hir/wgmma_accumulator_stmatrix.py
tests/nvidia/cuda/fixtures/schedule/hir/wgmma_b_mn_major_grouped_n64.py
tests/nvidia/cuda/fixtures/schedule/hir/wgmma_b_mn_major_one_atom_column_slice.py
tests/nvidia/cuda/fixtures/schedule/hir/wgmma_b_mn_major_two_atom_column_slice.py
tests/nvidia/cuda/fixtures/schedule/hir/wgmma_b_mn_major_wide_lbo.py
tests/nvidia/cuda/fixtures/schedule/hir/wgmma_b_mn_major_window_unit_mode.py
tests/nvidia/cuda/fixtures/schedule/hir/wgmma_b_nk.py
tests/nvidia/cuda/fixtures/schedule/hir/wgmma_cast_between_schedules.py
tests/nvidia/cuda/fixtures/schedule/hir/wgmma_cp_async_loads.py
tests/nvidia/cuda/fixtures/schedule/hir/wgmma_cta_grid_4x17.py
tests/nvidia/cuda/fixtures/schedule/hir/wgmma_explicit_windows.py
tests/nvidia/cuda/fixtures/schedule/hir/wgmma_k_slices_of_wide_run.py
tests/nvidia/cuda/fixtures/schedule/hir/wgmma_n16_within_warpgroup_share.py
tests/nvidia/cuda/fixtures/schedule/hir/wgmma_one_tile_of_larger_output.py
tests/nvidia/cuda/fixtures/schedule/hir/wgmma_repeat_along_k.py
tests/nvidia/cuda/fixtures/schedule/hir/wgmma_repeat_along_n_order.py
tests/nvidia/cuda/fixtures/schedule/hir/wgmma_rs_a_from_accumulator.py
tests/nvidia/cuda/fixtures/schedule/hir/wgmma_rs_a_from_smem.py
tests/nvidia/cuda/fixtures/schedule/hir/wgmma_swizzled_smem.py
tests/nvidia/cuda/fixtures/schedule/hir/wgmma_tma_3stage.py
tests/nvidia/cuda/fixtures/schedule/hir/wgmma_two_schedules.py
tests/nvidia/cuda/fixtures/schedule/hir/zero_trip_insert_slice.py
tests/nvidia/cuda/fixtures/schedule/hir/dim/row_copy.py
tests/nvidia/cuda/fixtures/schedule/plain/__init__.py
tests/nvidia/cuda/fixtures/schedule/plain/chunk_rmsnorm.py
tests/nvidia/cuda/fixtures/schedule/plain/fp8_block_scaled_gemm.py
tests/nvidia/cuda/fixtures/schedule/plain/gemm_8192x17408x5120_cta_grid.candidates.txt
tests/nvidia/cuda/fixtures/schedule/plain/gemm_8192x17408x5120_cta_grid.py
tests/nvidia/cuda/fixtures/schedule/plain/gemm_relu_gemm_smem_staged.py
tests/nvidia/cuda/fixtures/schedule/plain/gemm_relu_gemm_tiled.py
tests/nvidia/cuda/fixtures/schedule/plain/gemm_relu_gemm_untiled.py
tests/nvidia/cuda/fixtures/schedule/plain/reshard_locations.py
tests/nvidia/cuda/fixtures/schedule/plain/sm89_e4m3_gemm.py
tests/nvidia/cuda/fixtures/schedule/plain/sparse_decode.py
tests/nvidia/cuda/fixtures/schedule/plain/unit_mesh_axis_loop_carry.py
tests/nvidia/cuda/fixtures/schedule/tir/captured_insert_update.py
tests/nvidia/cuda/fixtures/schedule/tir/child_weight.py
tests/nvidia/cuda/fixtures/schedule/tir/cta_submesh_thread_scope.py
tests/nvidia/cuda/fixtures/schedule/tir/fp8_block_scaled_gemm.py
tests/nvidia/cuda/fixtures/schedule/tir/gemm_8192x17408x5120_register_store.py
tests/nvidia/cuda/fixtures/schedule/tir/gemm_8192x17408x5120_tma_store.py
tests/nvidia/cuda/fixtures/schedule/tir/inplace_output_update.py
tests/nvidia/cuda/fixtures/schedule/tir/loop_carry_from_param.py
tests/nvidia/cuda/fixtures/schedule/tir/loop_carry_rebind.py
tests/nvidia/cuda/fixtures/schedule/tir/loop_carry_window.py
tests/nvidia/cuda/fixtures/schedule/tir/loop_outputs.py
tests/nvidia/cuda/fixtures/schedule/tir/loop_variable_rebound.py
tests/nvidia/cuda/fixtures/schedule/tir/mesh_capture_outside.py
tests/nvidia/cuda/fixtures/schedule/tir/mesh_views.py
tests/nvidia/cuda/fixtures/schedule/tir/mesh_zeros_submesh.py
tests/nvidia/cuda/fixtures/schedule/tir/module_instances.py
tests/nvidia/cuda/fixtures/schedule/tir/register_arange.py
tests/nvidia/cuda/fixtures/schedule/tir/register_full_like.py
tests/nvidia/cuda/fixtures/schedule/tir/register_index_window.py
tests/nvidia/cuda/fixtures/schedule/tir/register_index_window_offset.py
tests/nvidia/cuda/fixtures/schedule/tir/reshard_views.py
tests/nvidia/cuda/fixtures/schedule/tir/scalar_binary.py
tests/nvidia/cuda/fixtures/schedule/tir/scalar_ceildiv_gate.py
tests/nvidia/cuda/fixtures/schedule/tir/sm80_mma_ldmatrix.py
tests/nvidia/cuda/fixtures/schedule/tir/sm89_e4m3_gemm.py
tests/nvidia/cuda/fixtures/schedule/tir/sparse_decode.py
tests/nvidia/cuda/fixtures/schedule/tir/staged_dynamic_inner.py
tests/nvidia/cuda/fixtures/schedule/tir/staged_nested.py
tests/nvidia/cuda/fixtures/schedule/tir/strided_return_window.py
tests/nvidia/cuda/fixtures/schedule/tir/submesh_slice_in_sibling.py
tests/nvidia/cuda/fixtures/schedule/tir/wgmma_a_k_major.py
tests/nvidia/cuda/fixtures/schedule/tir/wgmma_a_mn_major.py
tests/nvidia/cuda/fixtures/schedule/tir/wgmma_b_mn_major_grouped_n64.py
tests/nvidia/cuda/fixtures/schedule/tir/wgmma_b_mn_major_wide_lbo.py
tests/nvidia/cuda/fixtures/schedule/tir/wgmma_b_nk.py
tests/nvidia/cuda/fixtures/schedule/tir/wgmma_cast_between_schedules.py
tests/nvidia/cuda/fixtures/schedule/tir/wgmma_cp_async_loads.py
tests/nvidia/cuda/fixtures/schedule/tir/wgmma_cta_grid_4x17.py
tests/nvidia/cuda/fixtures/schedule/tir/wgmma_explicit_windows.py
tests/nvidia/cuda/fixtures/schedule/tir/wgmma_k_slices_of_wide_run.py
tests/nvidia/cuda/fixtures/schedule/tir/wgmma_one_tile_of_larger_output.py
tests/nvidia/cuda/fixtures/schedule/tir/wgmma_repeat_along_k.py
tests/nvidia/cuda/fixtures/schedule/tir/wgmma_repeat_along_n_order.py
tests/nvidia/cuda/fixtures/schedule/tir/wgmma_rs_a_from_accumulator.py
tests/nvidia/cuda/fixtures/schedule/tir/wgmma_rs_a_from_smem.py
tests/nvidia/cuda/fixtures/schedule/tir/wgmma_swizzled_smem.py
tests/nvidia/cuda/fixtures/schedule/tir/wgmma_tma_3stage.py
tests/nvidia/cuda/fixtures/schedule/tir/wgmma_two_schedules.py
tests/nvidia/cuda/fixtures/schedule/tir/zero_trip_insert_slice.py
tests/nvidia/cuda/fixtures/shapes/composed_leaf_source.py
tests/nvidia/cuda/fixtures/shapes/matmul_programs.py
tests/nvidia/cuda/fixtures/shapes/scaled_modules.py
tests/nvidia/cuda/fixtures/shapes/tile_window_syntax.py
tests/nvidia/cuda/fixtures/shapes/window_programs.py
tests/nvidia/cuda/fixtures/tir/async_sync.py
tests/nvidia/cuda/fixtures/tir/e4m3_gemm.py
tests/nvidia/cuda/fixtures/tir/mma.py
tests/nvidia/cuda/fixtures/tir/split_stage.py
tests/nvidia/cuda/fixtures/tir/square.py
tests/nvidia/cuda/fixtures/tir/sync.py
tests/nvidia/cuda/inspection/__init__.py
tests/nvidia/cuda/inspection/test_canonical_roundtrip.py
tests/nvidia/cuda/inspection/test_module_tree_roundtrip.py
tests/nvidia/cuda/inspection/test_python_printer.py
tests/nvidia/cuda/inspection/test_roundtrip.py
tests/nvidia/cuda/inspection/test_tir_roundtrip.py
tests/nvidia/cuda/installed/__init__.py
tests/nvidia/cuda/installed/conftest.py
tests/nvidia/cuda/installed/qwen3_1_7b_l3.py
tests/nvidia/cuda/installed/smoke_analyze.py
tests/nvidia/cuda/installed/smoke_check.py
tests/nvidia/cuda/installed/smoke_models.py
tests/nvidia/cuda/installed/smoke_shipped.py
tests/nvidia/cuda/installed/smoke_spec.py
tests/nvidia/cuda/installed/smoke_target_cli.py
tests/nvidia/cuda/installed/smoke_tutorial.py
tests/nvidia/cuda/installed/models/__init__.py
tests/nvidia/cuda/installed/models/conftest.py
tests/nvidia/cuda/installed/models/contract.py
tests/nvidia/cuda/installed/models/smoke_deepseek_v4_flash.py
tests/nvidia/cuda/installed/models/smoke_gemma2_2b.py
tests/nvidia/cuda/installed/models/smoke_kimi_linear_48b_a3b.py
tests/nvidia/cuda/installed/models/smoke_minicpm3_4b.py
tests/nvidia/cuda/installed/models/smoke_qwen2_5_1_5b.py
tests/nvidia/cuda/installed/models/smoke_qwen3_1_7b.py
tests/nvidia/cuda/installed/models/smoke_qwen3_5_35b_a3b.py
tests/nvidia/cuda/installed/smoke_target/__init__.py
tests/nvidia/cuda/installed/smoke_target/smoke_registry.py
tests/nvidia/cuda/installed/smoke_target/smoke_v100.py
tests/nvidia/cuda/installed/smoke_target/smoke_vendor_npu.py
tests/nvidia/cuda/installed/smoke_target/hw/__init__.py
tests/nvidia/cuda/installed/smoke_target/hw/vendor_sm70.toml
tests/nvidia/cuda/installed/smoke_target/hw/vendor_v100_sxm2_32gb.toml
tests/nvidia/cuda/integration/__init__.py
tests/nvidia/cuda/integration/test_dynamic_cta_tir_handwritten.py
tests/nvidia/cuda/integration/test_dynamic_shape_dispatch.py
tests/nvidia/cuda/integration/test_host_launch.py
tests/nvidia/cuda/integration/test_rmsnorm_quant.py
tests/nvidia/cuda/integration/test_tir_control_flow.py
tests/nvidia/cuda/integration/models/__init__.py
tests/nvidia/cuda/integration/models/deepseek_v4_flash/__init__.py
tests/nvidia/cuda/integration/models/deepseek_v4_flash/test_case.py
tests/nvidia/cuda/integration/models/deepseek_v4_flash/test_causal_lm_e2e.py
tests/nvidia/cuda/integration/models/deepseek_v4_flash/test_moe.py
tests/nvidia/cuda/integration/models/kimi_linear_48b_a3b/__init__.py
tests/nvidia/cuda/integration/models/kimi_linear_48b_a3b/test_kda.py
tests/nvidia/cuda/integration/models/qwen3_5_35b_a3b/__init__.py
tests/nvidia/cuda/integration/models/qwen3_5_35b_a3b/test_provenance.py
tests/nvidia/cuda/ir/__init__.py
tests/nvidia/cuda/ir/test_copy_reduce_async_tensor.py
tests/nvidia/cuda/ir/test_visitor.py
tests/nvidia/cuda/ir/atoms/__init__.py
tests/nvidia/cuda/ir/atoms/_cute_reference.py
tests/nvidia/cuda/ir/atoms/_operand_layout.py
tests/nvidia/cuda/ir/atoms/cute_reference.cpp
tests/nvidia/cuda/ir/atoms/test_ldmatrix.py
tests/nvidia/cuda/ir/atoms/test_mma.py
tests/nvidia/cuda/ir/atoms/test_stmatrix.py
tests/nvidia/cuda/ir/atoms/test_wgmma.py
tests/nvidia/cuda/ir/core/__init__.py
tests/nvidia/cuda/ir/core/test_dim_substitution.py
tests/nvidia/cuda/ir/core/test_gqa_online.py
tests/nvidia/cuda/ir/core/test_specialize.py
tests/nvidia/cuda/models/__init__.py
tests/nvidia/cuda/models/corpus.py
tests/nvidia/cuda/models/registry.py
tests/nvidia/cuda/models/access_footprint/__init__.py
tests/nvidia/cuda/models/access_footprint/case.py
tests/nvidia/cuda/models/access_footprint/model.py
tests/nvidia/cuda/models/deepseek_v4_flash/__init__.py
tests/nvidia/cuda/models/deepseek_v4_flash/case.py
tests/nvidia/cuda/models/deepseek_v4_flash/hf_alias.py
tests/nvidia/cuda/models/deepseek_v4_flash/reference.py
tests/nvidia/cuda/models/deepseek_v4_flash/runtime.py
tests/nvidia/cuda/models/gemma2_2b/__init__.py
tests/nvidia/cuda/models/gemma2_2b/case.py
tests/nvidia/cuda/models/gemma2_2b/reference.py
tests/nvidia/cuda/models/kimi_linear_48b_a3b/__init__.py
tests/nvidia/cuda/models/kimi_linear_48b_a3b/case.py
tests/nvidia/cuda/models/kimi_linear_48b_a3b/reference.py
tests/nvidia/cuda/models/minicpm3_4b/__init__.py
tests/nvidia/cuda/models/minicpm3_4b/case.py
tests/nvidia/cuda/models/minicpm3_4b/reference.py
tests/nvidia/cuda/models/qwen2_5_1_5b/__init__.py
tests/nvidia/cuda/models/qwen2_5_1_5b/case.py
tests/nvidia/cuda/models/qwen2_5_1_5b/reference.py
tests/nvidia/cuda/models/qwen3_1_7b/__init__.py
tests/nvidia/cuda/models/qwen3_1_7b/case.py
tests/nvidia/cuda/models/qwen3_1_7b/reference.py
tests/nvidia/cuda/models/qwen3_5_35b_a3b/__init__.py
tests/nvidia/cuda/models/qwen3_5_35b_a3b/case.py
tests/nvidia/cuda/models/qwen3_5_35b_a3b/reference.py
tests/nvidia/cuda/ops/__init__.py
tests/nvidia/cuda/ops/ir/__init__.py
tests/nvidia/cuda/ops/ir/test_arange.py
tests/nvidia/cuda/ops/ir/test_cache_update.py
tests/nvidia/cuda/ops/ir/test_local.py
tests/nvidia/cuda/ops/ir/test_matmul.py
tests/nvidia/cuda/ops/ir/test_reshard.py
tests/nvidia/cuda/ops/ir/test_where.py
tests/nvidia/cuda/ops/tir/__init__.py
tests/nvidia/cuda/ops/tir/targets.py
tests/nvidia/cuda/ops/tir/test_copy.py
tests/nvidia/cuda/ops/tir/test_copy_async.py
tests/nvidia/cuda/ops/tir/test_dot.py
tests/nvidia/cuda/ops/tir/test_elementwise.py
tests/nvidia/cuda/ops/tir/test_launch.py
tests/nvidia/cuda/ops/tir/test_mbarrier.py
tests/nvidia/cuda/ops/tir/test_mma.py
tests/nvidia/cuda/ops/tir/test_reduce.py
tests/nvidia/cuda/ops/tir/test_swizzle.py
tests/nvidia/cuda/ops/tir/test_sync.py
tests/nvidia/cuda/ops/tir/test_tma.py
tests/nvidia/cuda/parser/__init__.py
tests/nvidia/cuda/parser/test_calls.py
tests/nvidia/cuda/parser/test_dimensions.py
tests/nvidia/cuda/parser/test_functions.py
tests/nvidia/cuda/parser/test_mesh_visibility.py
tests/nvidia/cuda/parser/test_roundtrip.py
tests/nvidia/cuda/parser/test_slices.py
tests/nvidia/cuda/passes/__init__.py
tests/nvidia/cuda/passes/test_host_entry.py
tests/nvidia/cuda/runtime/__init__.py
tests/nvidia/cuda/runtime/test_cuda_static_asserts.py
tests/nvidia/cuda/runtime/test_jit.py
tests/nvidia/cuda/runtime/cuda/static_asserts.cu
tests/nvidia/cuda/runtime/resource/__init__.py
tests/nvidia/cuda/runtime/resource/test_child_module_resources.py
tests/nvidia/cuda/runtime/resource/test_placed_launch.py
tests/nvidia/cuda/runtime/resource/test_resource_device.py
tests/nvidia/cuda/runtime/resource/test_weight_loading.py
tests/nvidia/cuda/scaffold/__init__.py
tests/nvidia/cuda/scaffold/test_scaffold.py
tests/nvidia/cuda/schedule/__init__.py
tests/nvidia/cuda/schedule/test_fixtures.py
tests/nvidia/cuda/schedule/test_storage_context.py
tests/nvidia/cuda/target/__init__.py
tests/nvidia/cuda/target/test_hardware_resources.py
tests/nvidia/cuda/target/test_target.py
tests/nvidia/cuda/target/test_target_facts.py
tests/nvidia/cuda/visitor_registry/__init__.py
tests/nvidia/cuda/visitor_registry/test_capability_admission.py
tests/nvidia/cuda/visitor_registry/test_visitor_registry.py