This is an automated email from the ASF dual-hosted git repository.

github-bot pushed a change to branch nightly
in repository https://gitbox.apache.org/repos/asf/tvm.git


    from d1ac1c0202 [KVCache] Fix the aux data syncing order of paged KV cache 
(#16988)
     add 1d4b9ea5c3 [UnitTest] Use pytest's scope='session' for 
tvm.testing.parameter (#16930)
     add fd820ade5f [Disco] Expose disco.Session.shutdown through the python 
API (#16979)
     add 29337449db [Cuda] Skip FreeDataSpace when CUDA driver is in 
inconsistent state (#16980)
     add eb242ec77b [DLight] Check for target in function attributes (#16958)
     add 0dfc5f955e [Unity] Check for transpose and dynamic shape in 
AdjustMatmulOrder (#16589)
     add 5b5f8d0f77 [QoL][IR] Provide std::hash and std::equal_to for IR 
Variable types (#16909)
     add c2d14ae872 [Relax][Transform] Handle identical PrimFunc with distinct 
VDevice (#16959)

No new revisions were added by this update.

Summary of changes:
 include/tvm/ir/expr.h                              |  29 ++++
 include/tvm/relax/analysis.h                       |  13 ++
 include/tvm/relax/expr.h                           |  30 ++++
 include/tvm/tir/var.h                              |  30 ++++
 python/tvm/dlight/base/transform.py                |  11 +-
 python/tvm/relax/analysis/__init__.py              |   1 +
 python/tvm/relax/analysis/analysis.py              |  27 ++++
 python/tvm/runtime/disco/session.py                |   4 +
 python/tvm/testing/utils.py                        |   2 +-
 src/arith/const_int_bound.cc                       |   2 +-
 src/arith/iter_affine_map.cc                       |  10 +-
 src/arith/modular_set.cc                           |   2 +-
 src/arith/rewrite_simplify.h                       |   2 +-
 src/contrib/msc/core/transform/set_expr_layout.cc  |   2 +-
 .../feature_extractor/per_store_feature.cc         |   2 +-
 .../multi_level_tiling_tensor_core.cc              |   6 +-
 src/relax/analysis/computable_at_compile_time.cc   |   2 +-
 src/relax/analysis/layout_transformation.cc        |   4 +-
 src/relax/analysis/struct_info_analysis.cc         |  49 +++++-
 src/relax/analysis/udchain.cc                      |   2 +-
 src/relax/analysis/well_formed.cc                  |  16 +-
 src/relax/backend/vm/codegen_vm.cc                 |   2 +-
 src/relax/backend/vm/codegen_vm_tir.cc             |   2 +-
 .../transform/lower_global_view_to_local_view.cc   |   4 +-
 src/relax/ir/expr_functor.cc                       |  11 ++
 src/relax/transform/adjust_matmul_order.cc         |  86 ++++++++---
 src/relax/transform/canonicalize_bindings.cc       |   4 +-
 src/relax/transform/convert_layout.cc              |   2 +-
 src/relax/transform/dataflow_inplace.cc            |  24 ++-
 src/relax/transform/dead_code_elimination.cc       |   7 +-
 src/relax/transform/expand_matmul_of_sum.cc        |   3 +-
 src/relax/transform/fuse_tir.cc                    |   9 +-
 src/relax/transform/infer_amp_utils.h              |   2 +-
 src/relax/transform/lambda_lift.cc                 |   4 +-
 src/relax/transform/lazy_transform_params.cc       |  12 +-
 src/relax/transform/legalize_ops.cc                | 112 +++++++++++---
 src/relax/transform/lift_transform_params.cc       |  21 +--
 src/relax/transform/merge_composite_functions.cc   |   2 +-
 src/relax/transform/split_call_tir_by_pattern.cc   |   2 +-
 src/relax/transform/topological_sort.cc            |   2 +-
 src/relax/transform/update_param_struct_info.cc    |   4 +-
 src/relay/analysis/call_graph.h                    |   6 +-
 src/runtime/cuda/cuda_device_api.cc                |  18 +++
 src/runtime/disco/session.cc                       |   2 +
 src/target/llvm/codegen_llvm.h                     |   2 +-
 src/target/source/codegen_c.h                      |   4 +-
 src/target/source/codegen_webgpu.cc                |   2 +-
 src/target/spirv/codegen_spirv.h                   |   2 +-
 src/tir/analysis/is_pure_function.cc               |   2 +-
 src/tir/analysis/verify_ssa.cc                     |   2 +-
 src/tir/analysis/verify_well_formed.cc             |   6 +-
 src/tir/ir/specialize.cc                           |   2 +-
 src/tir/ir/tir_visitor_with_path.cc                |   2 +-
 src/tir/schedule/analysis/analysis.cc              |   4 +-
 src/tir/schedule/primitive/cache_read_write.cc     |  12 +-
 src/tir/schedule/primitive/reduction.cc            |   4 +-
 src/tir/transforms/compact_buffer_region.cc        |  20 +--
 src/tir/transforms/inject_permuted_layout.cc       |   2 +-
 src/tir/transforms/inject_software_pipeline.cc     |   2 +-
 src/tir/transforms/ir_utils.cc                     |  45 +++++-
 src/tir/transforms/ir_utils.h                      |   3 +-
 src/tir/transforms/lower_custom_datatypes.cc       |   2 +-
 src/tir/transforms/lower_opaque_block.cc           |   4 +-
 src/tir/transforms/storage_flatten.cc              |   2 +-
 src/tir/transforms/texture_flatten.cc              |   2 +-
 src/tir/transforms/thread_storage_sync.cc          |   2 +-
 src/tir/transforms/transform_mma_buffer_layout.cc  |   2 +-
 src/tir/transforms/unroll_loop.cc                  |   7 +-
 src/tir/transforms/unsupported_dtype_legalize.cc   |  17 +--
 src/tir/transforms/vectorize_loop.cc               |   2 +-
 src/tir/usmp/analysis/extract_buffer_info.cc       |   2 +-
 src/tir/usmp/transform/create_io_allocates.cc      |   8 +-
 tests/python/dlight/test_gpu_fallback.py           |  78 ++++++++++
 .../relax/test_analysis_struct_info_analysis.py    |  43 ++++++
 .../relax/test_transform_adjust_matmul_order.py    | 164 +++++++++++++++++++++
 tests/python/relax/test_transform_legalize_ops.py  |  81 ++++++++++
 tests/python/testing/test_tvm_testing_features.py  |  11 ++
 77 files changed, 922 insertions(+), 208 deletions(-)

Reply via email to