This is an automated email from the ASF dual-hosted git repository.
masahi pushed a change to branch unity
in repository https://gitbox.apache.org/repos/asf/tvm.git
omit 7c35267756 [Fix] add TVM_DLL to disco functions (#16258)
omit 09acbc8a78 [Unity] Bump fpA_intB_gemm (#16244)
omit 95f1b5c0e8 [Unity] Hot Fix Unity CI (#16256)
omit 76e239e2e1 [Unity] Fix Cutlass Codegen for Dense (#16252)
omit a0e58987b0 [Unity][nn.Module] Refactor `ExternModule` (#16247)
omit 2d0d4e46a9 [Unity] Enable spot nodes in CI (#16253)
omit f794db4373 [Unity] Avoid to use `std::regex` (#16249)
omit 5b1fa29838 [Unity][VM] Allow `pipeline=None` in `relax.build` (#16246)
omit 8edfee8574 [Unity][MSC][M2.4] Add quantizer for quantize model (#16228)
omit a2e19d21eb [Unity] Fix IndexDataTypeNormalizer so that it correctly
handles corner case (#16245)
omit cd9445d63b [Unity][lm_support] window kvcache sink (#16240)
omit e1964eceb5 [Unity] Add runtime debugging method to RelaxVM (#16238)
omit 6118b770b1 [Unity] Improved error checking for DataflowBlock in nested
SeqExpr (#16195)
omit 674167805c Revert "[Unity] Fix IndexDataTypeNormalizer so that it
correctly handles corner case" (#16241)
omit e100a13737 [Unity] Fix legalizing strided slice (#16232)
omit f7b0193f9d [Unity] Fix IndexDataTypeNormalizer so that it correctly
handles corner case (#16235)
omit fe89ccc360 [Unity][Transform] Pass for automatically extracting
DataflowBlocks (#16204)
omit cbcb67c047 [Unity][Frontend] Add the `sum` op to frontend ops (#16225)
omit 943508a295 [Unity] Fix typo in dlight fallback rule (#16230)
omit af14fbbbe1 [Relax] Fix to enable emit_te of topi scan/sort kernels
(#16226)
omit c6d4926529 [Dlight] Fix NormalizePrimFunc with scalar block (#16156)
omit 2772fb072a [Unity] Fix upstream tests that fail on unity branch
(#16196)
omit 8241385f59 [Unity] De-duplicate calls to TensorStructInfo constructor
(#16209)
omit b5b980e33a [Unity] Support out dtype for nn.Linear and nn.MultiLinear
(#16220)
omit f18d186559 [Unity] Speed up NormalizeGlobalVar (#16219)
omit 35e8404f17 [Disco] Expose `DiscoWorker` and `ndarray_cache_support` in
header (#16153)
omit e0518da2a5 [Unity][MSC][M2.3] Add tracker for track layer datas
(#16207)
omit 58e622b74d [Unity][Transform] Implement Relax function inlining
(#16194)
omit 03fc4f6f03 [Dlight] Change max_threads on CUDA (#16203)
omit ebbad09cd5 [Unity] Upgrade cutlass_fpA_intB_gemm (#16206)
omit d0504027bb [Unity] Update FlashInfer (#16208)
omit 4e8c975700 [Unity][Bugfix] Fix
`tests/python/topi/test_topi_transform.py::test_relax_dynamic_strided_slice`
(#16205)
omit 34fd234f55 [Unity] Check usage location when canonicalizing trivial
bindings (#16193)
omit 3c7067d6ed [Unity] Minor: Remove debug logging (#16200)
omit 8f95f6147a [Unity] [Transform] Remove iteration over functions in
function pass (#16173)
omit a2f55a8812 [WEBGPU] Update to latest compilationHints API (#16197)
omit 9e4e17ca88 [Unity][WebGPU] Get params from cache by name (#16198)
omit ed2772f9c8 [Unity][MSC][M2.1] Add pruner for model pruning (#16186)
omit 74667b97f0 [Unity] Enable ccache for `nn.SourceModule` (#16189)
omit fc324d0f2c [Unity][Transform] Implement RemoveUnusedParameters (#16116)
omit fe9d2fe57d [Unity][Transform] Implement ExpandTupleArguments (#16115)
omit d6015c5643 [Unity][BugFix] Fix a bug in relax gelu_tanh computation
(#16188)
omit d52a9bf388 [Unity][Transform] Implement RemoveUnusedOutputs (#16117)
omit 68443482c9 [Unity][Bugfix] Handle symbolic matching with
non-structural match (#15994)
omit 85389efa2c [Unity][BYOC] Fix Flash var_len attention with sliding
window (#16185)
omit a6adaae5ef [Unity][DistIR] LowerDistIR (#16169)
omit 8a6184ccfa [Unity, BYOC] Add check for leaking intemediate variables
for cublas and cudnn (#16175)
omit c640d0a3c9 [Unity][Web] Fix missing function NVTXScopedRange for web
(#16177)
omit 64fe5a8a89 [Unity][DistIR] Add DTensor struct info propagation rule
for stop_lift_params (#16170)
omit af803cf7b4 [Unity][DLight] Fix `general_reduction` for GroupNorm
(#16161)
omit 8f24a272a0 [Unity][MSC][M2.1] Add Manager for compile pipeline (#16163)
omit 2dcb8716e8 [Unity][BlockBuilder] Depracate `BlockBuilder.get()` and
change it to `BlockBuilder.finalize()` (#16090)
omit 1de8b347d1 [Unity][DistIR] LowerGlobalViewToLocalView (#16095)
omit 756ce9917f [Unity][3rdparty] Remove TVM in 3rdparty of FlashInfer
(#16155)
omit aae1112a65 [Unity] Support constant args in `nn.ExternModule` (#16130)
new 2f7691e245 disable sinfo check
new adb9edfff0 (Hacky) VM allocator changes to support batched serving
with memory profiling
new 6e3c8d34cd use fp32 accum in cublas
new 605a9ad8ce Add vllm kernels
new 1fda9ad03e fix fp32 accum not getting enabled
new abde85edbc fix window_size_left param for var len attention
new 8e448d8f29 window_size_left should be max_seqlen_k, not num_key for
the var_len case
new e73558e41d WA for H100
new d0634f26ac enable sm90 codegen for thrust and vllm
new f19ab37142 update FT rev to support H100
new bbb8f40d25 add kernel for copying cache blocks
new 33989b48d9 moe update
new c606a069c3 kernel
new 02f6f7daf2 fix
new 976a951728 fix
new fffbd9b79c fix
new f238c3b264 fix
new 0760ab0929 cleanup
new c796f47f95 fix
This update added new revisions after undoing existing revisions.
That is to say, some revisions that were in the old version of the
branch are not in the new version. This situation occurs
when a user --force pushes a change and generates a repository
containing something like this:
* -- * -- B -- O -- O -- O (7c35267756)
\
N -- N -- N refs/heads/unity (c796f47f95)
You should already have received notification emails for all of the O
revisions, and so the following emails describe only the N revisions
from the common base, B.
Any revisions marked "omit" are not gone; other references still
refer to them. Any revisions marked "discard" are gone forever.
The 19 revisions listed above as "new" are entirely new to this
repository and will be described in separate emails. The revisions
listed as "add" were already present in the repository and have only
been added to this reference.
Summary of changes:
.gitmodules | 2 +-
3rdparty/cutlass_fpA_intB_gemm | 2 +-
3rdparty/flashinfer | 2 +-
CMakeLists.txt | 2 +-
ci/jenkins/unity_jenkinsfile.groovy | 100 +-
cmake/config.cmake | 4 +
cmake/modules/CUDA.cmake | 6 +
cmake/modules/contrib/CUTLASS.cmake | 5 +
.../Makefile => cmake/modules/contrib/vllm.cmake | 26 +-
include/tvm/relax/block_builder.h | 9 -
include/tvm/relax/distributed/transform.h | 13 -
include/tvm/relax/struct_info.h | 4 +-
include/tvm/relax/transform.h | 36 -
include/tvm/runtime/disco/session.h | 20 +-
include/tvm/runtime/memory/memory_manager.h | 4 +-
include/tvm/topi/transform.h | 25 +-
....cutlass_fpA_intB_gemm.txt => LICENSE.vllm.txt} | 1 -
python/tvm/contrib/cc.py | 52 +-
python/tvm/contrib/cutlass/gen_conv2d.py | 2 +-
python/tvm/contrib/cutlass/gen_gemm.py | 2 +-
python/tvm/contrib/cutlass/gen_tensor_op.py | 6 +-
python/tvm/contrib/msc/core/codegen/sources.py | 56 +-
python/tvm/contrib/msc/core/ir/graph.py | 242 +--
python/tvm/contrib/msc/core/runtime/runner.py | 482 ++----
python/tvm/contrib/msc/core/tools/__init__.py | 23 -
python/tvm/contrib/msc/core/tools/execute.py | 386 -----
.../tvm/contrib/msc/core/tools/prune/__init__.py | 20 -
python/tvm/contrib/msc/core/tools/prune/method.py | 118 --
python/tvm/contrib/msc/core/tools/prune/pruner.py | 468 ------
.../contrib/msc/core/tools/quantize/__init__.py | 20 -
.../tvm/contrib/msc/core/tools/quantize/method.py | 472 ------
.../contrib/msc/core/tools/quantize/quantizer.py | 249 ---
python/tvm/contrib/msc/core/tools/tool.py | 1483 ------------------
.../tvm/contrib/msc/core/tools/track/__init__.py | 20 -
python/tvm/contrib/msc/core/tools/track/method.py | 102 --
python/tvm/contrib/msc/core/tools/track/tracker.py | 185 ---
python/tvm/contrib/msc/core/utils/dataset.py | 415 +----
python/tvm/contrib/msc/core/utils/file.py | 109 +-
python/tvm/contrib/msc/core/utils/info.py | 161 +-
python/tvm/contrib/msc/core/utils/log.py | 21 +-
python/tvm/contrib/msc/core/utils/message.py | 71 +-
python/tvm/contrib/msc/core/utils/namespace.py | 12 +-
python/tvm/contrib/msc/core/utils/register.py | 134 +-
.../msc/framework/tensorflow/runtime/runner.py | 36 +-
.../msc/framework/tensorflow/tools/__init__.py | 21 -
.../framework/tensorflow/tools/prune/__init__.py | 19 -
.../msc/framework/tensorflow/tools/prune/pruner.py | 55 -
.../tensorflow/tools/quantize/__init__.py | 19 -
.../tensorflow/tools/quantize/quantizer.py | 55 -
.../framework/tensorflow/tools/track/__init__.py | 19 -
.../framework/tensorflow/tools/track/tracker.py | 55 -
.../msc/framework/tensorrt/codegen/codegen.py | 40 +-
.../msc/framework/tensorrt/codegen/sources.py | 172 +--
.../msc/framework/tensorrt/frontend/translate.py | 38 +-
.../msc/framework/tensorrt/runtime/runner.py | 90 +-
.../msc/framework/tensorrt/tools/__init__.py | 21 -
.../msc/framework/tensorrt/tools/prune/__init__.py | 19 -
.../msc/framework/tensorrt/tools/prune/pruner.py | 55 -
.../framework/tensorrt/tools/quantize/__init__.py | 20 -
.../framework/tensorrt/tools/quantize/method.py | 149 --
.../framework/tensorrt/tools/quantize/quantizer.py | 366 -----
.../msc/framework/tensorrt/tools/track/__init__.py | 19 -
.../msc/framework/tensorrt/tools/track/tracker.py | 159 --
.../msc/framework/torch/frontend/translate.py | 2 +-
.../contrib/msc/framework/torch/runtime/runner.py | 2 -
.../contrib/msc/framework/torch/tools/__init__.py | 21 -
.../msc/framework/torch/tools/prune/__init__.py | 19 -
.../msc/framework/torch/tools/prune/pruner.py | 55 -
.../msc/framework/torch/tools/quantize/__init__.py | 20 -
.../msc/framework/torch/tools/quantize/method.py | 237 ---
.../framework/torch/tools/quantize/quantizer.py | 55 -
.../msc/framework/torch/tools/track/__init__.py | 19 -
.../msc/framework/torch/tools/track/tracker.py | 55 -
.../contrib/msc/framework/tvm/runtime/runner.py | 34 +-
.../contrib/msc/framework/tvm/tools/__init__.py | 21 -
.../msc/framework/tvm/tools/prune/__init__.py | 19 -
.../msc/framework/tvm/tools/prune/pruner.py | 55 -
.../msc/framework/tvm/tools/quantize/__init__.py | 20 -
.../msc/framework/tvm/tools/quantize/method.py | 204 ---
.../msc/framework/tvm/tools/quantize/quantizer.py | 167 ---
.../msc/framework/tvm/tools/track/__init__.py | 19 -
.../msc/framework/tvm/tools/track/tracker.py | 155 --
python/tvm/contrib/msc/pipeline/__init__.py | 19 -
python/tvm/contrib/msc/pipeline/manager.py | 883 -----------
python/tvm/dlight/gpu/fallback.py | 10 +-
python/tvm/dlight/gpu/general_reduction.py | 19 +-
python/tvm/dlight/gpu/utils.py | 2 +-
python/tvm/relax/backend/contrib/cublas.py | 3 -
python/tvm/relax/backend/contrib/cudnn.py | 3 -
python/tvm/relax/backend/contrib/cutlass.py | 32 +-
python/tvm/relax/backend/utils.py | 43 -
python/tvm/relax/block_builder.py | 48 +-
python/tvm/relax/distributed/transform/__init__.py | 7 +-
.../tvm/relax/distributed/transform/transform.py | 22 -
python/tvm/relax/expr.py | 5 -
python/tvm/relax/frontend/nn/__init__.py | 14 +-
python/tvm/relax/frontend/nn/core.py | 349 +++--
python/tvm/relax/frontend/nn/exporter.py | 314 ----
python/tvm/relax/frontend/nn/extern.py | 392 -----
python/tvm/relax/frontend/nn/modules.py | 79 +-
python/tvm/relax/frontend/nn/op.py | 269 ++--
python/tvm/relax/frontend/nn/spec.py | 355 ++++-
python/tvm/relax/ir/instrument.py | 2 +-
python/tvm/relax/op/distributed/__init__.py | 7 +-
python/tvm/relax/op/distributed/distributed.py | 53 +-
python/tvm/relax/pipeline.py | 2 +-
python/tvm/relax/transform/__init__.py | 7 -
.../tvm/relax/transform/attach_external_modules.py | 52 -
python/tvm/relax/transform/legalize_ops/index.py | 12 +
python/tvm/relax/transform/legalize_ops/nn.py | 14 +-
.../relax/transform/optimize_layout_transform.py | 37 +-
.../relax/transform/remove_redundant_reshape.py | 37 +-
python/tvm/relax/transform/transform.py | 73 -
python/tvm/relax/vm_build.py | 44 +-
python/tvm/runtime/disco/process_pool.py | 16 +-
python/tvm/runtime/disco/session.py | 3 +-
python/tvm/runtime/ndarray.py | 31 +-
python/tvm/runtime/relax_vm.py | 12 +-
.../tvm/script/ir_builder/relax/distributed/ir.py | 1 -
python/tvm/script/parser/relax/dist.py | 1 -
python/tvm/script/parser/relax/parser.py | 3 -
python/tvm/target/detect_target.py | 23 +-
python/tvm/testing/utils.py | 5 +-
rust/tvm/src/ir/module.rs | 14 +-
src/arith/ir_visitor_with_analyzer.cc | 2 +-
src/contrib/msc/core/codegen/base_codegen.h | 24 +-
src/contrib/msc/core/codegen/code_stack.h | 8 +-
src/contrib/msc/core/codegen/codegen_utils.cc | 2 +-
src/contrib/msc/core/codegen/codegen_utils.h | 75 +-
src/contrib/msc/core/codegen/cpp_codegen.h | 90 +-
src/contrib/msc/core/codegen/py_codegen.h | 59 +-
src/contrib/msc/core/ir/graph.cc | 447 +-----
src/contrib/msc/core/ir/graph.h | 201 +--
src/contrib/msc/core/printer/python_printer.cc | 2 +-
src/contrib/msc/core/transform/set_expr_name.cc | 110 +-
src/contrib/msc/core/utils.cc | 20 +-
src/contrib/msc/framework/tensorflow/codegen.cc | 4 +-
src/contrib/msc/framework/tensorrt/codegen.cc | 97 +-
src/contrib/msc/framework/tensorrt/codegen.h | 10 -
src/contrib/msc/framework/tensorrt/codegen_utils.h | 17 +-
.../msc/framework/tensorrt/tensorrt_opcode.cc | 15 +-
.../msc/framework/tensorrt/tensorrt_opcode.h | 2 +-
src/contrib/msc/framework/torch/codegen.cc | 22 +-
src/contrib/msc/framework/torch/codegen_utils.h | 4 +-
src/contrib/msc/framework/torch/torch_opcode.cc | 46 -
src/contrib/msc/framework/torch/torch_opcode.h | 5 +-
src/contrib/msc/framework/tvm/codegen.cc | 40 +-
src/contrib/msc/framework/tvm/relax_opcode.cc | 17 +-
src/contrib/msc/framework/tvm/relax_opcode.h | 2 +-
src/ir/module.cc | 16 +-
src/node/script_printer.cc | 15 +-
src/relax/analysis/well_formed.cc | 5 +-
src/relax/distributed/transform/lower_distir.cc | 271 ----
.../transform/lower_global_view_to_local_view.cc | 442 ------
src/relax/ir/block_builder.cc | 38 +-
src/relax/ir/dataflow_matcher.cc | 7 +-
src/relax/ir/struct_info.cc | 9 +-
src/relax/op/ccl/ccl.cc | 11 +-
src/relax/op/distributed/ccl.cc | 43 -
src/relax/op/distributed/distributed.cc | 60 +-
src/relax/op/distributed/op.cc | 10 -
src/relax/op/image/resize.cc | 10 +-
src/relax/op/nn/attention.cc | 5 +-
src/relax/op/nn/convolution.cc | 40 +-
src/relax/op/nn/nn.cc | 50 +-
src/relax/op/nn/pooling.cc | 20 +-
src/relax/op/tensor/binary.cc | 20 +-
src/relax/op/tensor/create.cc | 5 +-
src/relax/op/tensor/index.cc | 51 +-
src/relax/op/tensor/manipulate.cc | 290 +++-
src/relax/op/tensor/search.cc | 22 +-
src/relax/op/tensor/set.cc | 39 +-
src/relax/op/tensor/statistical.cc | 45 +-
src/relax/transform/canonicalize_bindings.cc | 106 +-
src/relax/transform/convert_dataflow.cc | 151 --
src/relax/transform/expand_tuple_arguments.cc | 187 ---
src/relax/transform/fuse_tir.cc | 96 +-
src/relax/transform/inline_functions.cc | 228 ---
src/relax/transform/normalize.cc | 106 --
src/relax/transform/remove_unused_outputs.cc | 326 ----
src/relax/transform/remove_unused_parameters.cc | 260 ----
src/runtime/contrib/cublas/cublas.cc | 9 +-
src/runtime/contrib/cublas/cublas_json_runtime.cc | 1 +
src/runtime/contrib/cudnn/cudnn_json_runtime.cc | 3 +-
src/runtime/contrib/cutlass/moe_compute_rows.cu | 45 +
src/runtime/contrib/cutlass/moe_gemm.cc | 101 ++
src/runtime/contrib/cutlass/weight_preprocess.cc | 30 +-
src/runtime/contrib/msc/tensorrt_runtime.cc | 71 +-
src/runtime/contrib/thrust/thrust.cu | 29 +
src/runtime/contrib/vllm/attention_kernels.cu | 509 +++++++
src/runtime/contrib/vllm/cache_alloc.cc | 55 +
src/runtime/contrib/vllm/cache_kernels.cu | 178 +++
src/runtime/contrib/vllm/dtype_float16.h | 688 +++++++++
src/runtime/cuda/cuda_device_api.cc | 8 -
src/runtime/disco/bcast_session.h | 3 +-
src/runtime/disco/builtin.cc | 9 +-
{include/tvm => src}/runtime/disco/builtin.h | 42 +-
src/runtime/disco/disco_worker_thread.h | 83 -
src/runtime/disco/loader.cc | 89 +-
src/runtime/disco/nccl/nccl.cc | 5 +-
src/runtime/disco/process_session.cc | 9 +-
src/runtime/disco/session.cc | 3 +-
src/runtime/disco/threaded_session.cc | 3 +-
src/runtime/disco/utils.h | 32 +-
src/runtime/disco/{disco_worker.cc => worker.cc} | 10 +-
.../disco_worker.h => src/runtime/disco/worker.h | 73 +-
src/runtime/memory/memory_manager.cc | 17 +
src/runtime/memory/naive_allocator.h | 2 +-
src/runtime/memory/pooled_allocator.h | 29 +-
src/runtime/relax_vm/builtin.cc | 29 -
src/runtime/relax_vm/lm_support.cc | 44 +-
src/runtime/relax_vm/ndarray_cache_support.cc | 170 ++-
.../runtime/relax_vm/ndarray_cache_support.h | 39 +-
src/script/printer/relax/call.cc | 7 +-
src/tir/ir/data_type_rewriter.cc | 7 +-
src/tir/schedule/transform.cc | 14 -
src/tir/schedule/transform.h | 9 -
src/tir/transforms/compact_buffer_region.cc | 2 +-
src/tir/transforms/unify_thread_binding.cc | 3 +-
src/topi/transform.cc | 3 +-
tests/python/contrib/test_ccache.py | 79 -
tests/python/contrib/test_msc/test_graph_build.py | 25 +-
tests/python/contrib/test_msc/test_manager.py | 263 ----
tests/python/contrib/test_msc/test_runner.py | 4 +-
tests/python/contrib/test_msc/test_tools.py | 257 ----
.../contrib/test_msc/test_translate_relax.py | 2 +-
tests/python/dlight/test_gpu_general_reduction.py | 256 +---
tests/python/dlight/test_gpu_reduction.py | 343 ++---
tests/python/dlight/test_primitives.py | 60 -
.../test_distributed_transform_lower_distir.py | 396 -----
...ributed_transform_lower_global_to_local_view.py | 1579 --------------------
tests/python/relax/frontend_nn_extern_module.cc | 69 -
tests/python/relax/test_blockbuilder_core.py | 295 +---
tests/python/relax/test_codegen_cutlass.py | 61 +-
tests/python/relax/test_contrib_vllm.py | 695 +++++++++
tests/python/relax/test_dataflow_pattern.py | 4 +-
tests/python/relax/test_frontend_nn_debug.py | 83 -
.../python/relax/test_frontend_nn_extern_module.py | 323 ++--
tests/python/relax/test_frontend_nn_modules.py | 55 +-
tests/python/relax/test_frontend_nn_op.py | 68 +-
tests/python/relax/test_inline_functions.py | 404 -----
tests/python/relax/test_runtime_builtin.py | 41 -
.../relax/test_transform_canonicalize_bindings.py | 311 +---
.../relax/test_transform_convert_dataflow.py | 493 ------
.../relax/test_transform_expand_tuple_args.py | 79 -
.../relax/test_transform_fuse_ops_by_pattern.py | 23 -
tests/python/relax/test_transform_fuse_tir.py | 157 +-
.../test_transform_inline_private_functions.py | 105 --
..._transform_legalize_ops_index_linear_algebra.py | 90 +-
.../python/relax/test_transform_legalize_ops_nn.py | 75 +-
.../relax/test_transform_normalize_global_var.py | 98 --
.../relax/test_transform_remove_unused_outputs.py | 123 --
.../test_transform_remove_unused_parameters.py | 101 --
tests/python/relay/test_json_compact.py | 20 +-
tests/python/relay/test_py_converter.py | 16 +-
tests/python/relay/test_vm.py | 34 +-
tests/python/topi/test_topi_transform.py | 21 +-
tests/scripts/task_config_build_gpu.sh | 1 -
tests/scripts/task_python_integration.sh | 2 +-
web/Makefile | 2 +-
web/emcc/wasm_runtime.cc | 1 -
web/package-lock.json | 12 +-
web/package.json | 2 +-
web/src/runtime.ts | 17 -
web/src/webgpu.ts | 7 +-
265 files changed, 5314 insertions(+), 20101 deletions(-)
copy apps/dso_plugin_module/Makefile => cmake/modules/contrib/vllm.cmake (61%)
copy licenses/{LICENSE.cutlass_fpA_intB_gemm.txt => LICENSE.vllm.txt} (99%)
delete mode 100644 python/tvm/contrib/msc/core/tools/__init__.py
delete mode 100644 python/tvm/contrib/msc/core/tools/execute.py
delete mode 100644 python/tvm/contrib/msc/core/tools/prune/__init__.py
delete mode 100644 python/tvm/contrib/msc/core/tools/prune/method.py
delete mode 100644 python/tvm/contrib/msc/core/tools/prune/pruner.py
delete mode 100644 python/tvm/contrib/msc/core/tools/quantize/__init__.py
delete mode 100644 python/tvm/contrib/msc/core/tools/quantize/method.py
delete mode 100644 python/tvm/contrib/msc/core/tools/quantize/quantizer.py
delete mode 100644 python/tvm/contrib/msc/core/tools/tool.py
delete mode 100644 python/tvm/contrib/msc/core/tools/track/__init__.py
delete mode 100644 python/tvm/contrib/msc/core/tools/track/method.py
delete mode 100644 python/tvm/contrib/msc/core/tools/track/tracker.py
delete mode 100644
python/tvm/contrib/msc/framework/tensorflow/tools/__init__.py
delete mode 100644
python/tvm/contrib/msc/framework/tensorflow/tools/prune/__init__.py
delete mode 100644
python/tvm/contrib/msc/framework/tensorflow/tools/prune/pruner.py
delete mode 100644
python/tvm/contrib/msc/framework/tensorflow/tools/quantize/__init__.py
delete mode 100644
python/tvm/contrib/msc/framework/tensorflow/tools/quantize/quantizer.py
delete mode 100644
python/tvm/contrib/msc/framework/tensorflow/tools/track/__init__.py
delete mode 100644
python/tvm/contrib/msc/framework/tensorflow/tools/track/tracker.py
delete mode 100644 python/tvm/contrib/msc/framework/tensorrt/tools/__init__.py
delete mode 100644
python/tvm/contrib/msc/framework/tensorrt/tools/prune/__init__.py
delete mode 100644
python/tvm/contrib/msc/framework/tensorrt/tools/prune/pruner.py
delete mode 100644
python/tvm/contrib/msc/framework/tensorrt/tools/quantize/__init__.py
delete mode 100644
python/tvm/contrib/msc/framework/tensorrt/tools/quantize/method.py
delete mode 100644
python/tvm/contrib/msc/framework/tensorrt/tools/quantize/quantizer.py
delete mode 100644
python/tvm/contrib/msc/framework/tensorrt/tools/track/__init__.py
delete mode 100644
python/tvm/contrib/msc/framework/tensorrt/tools/track/tracker.py
delete mode 100644 python/tvm/contrib/msc/framework/torch/tools/__init__.py
delete mode 100644
python/tvm/contrib/msc/framework/torch/tools/prune/__init__.py
delete mode 100644 python/tvm/contrib/msc/framework/torch/tools/prune/pruner.py
delete mode 100644
python/tvm/contrib/msc/framework/torch/tools/quantize/__init__.py
delete mode 100644
python/tvm/contrib/msc/framework/torch/tools/quantize/method.py
delete mode 100644
python/tvm/contrib/msc/framework/torch/tools/quantize/quantizer.py
delete mode 100644
python/tvm/contrib/msc/framework/torch/tools/track/__init__.py
delete mode 100644
python/tvm/contrib/msc/framework/torch/tools/track/tracker.py
delete mode 100644 python/tvm/contrib/msc/framework/tvm/tools/__init__.py
delete mode 100644 python/tvm/contrib/msc/framework/tvm/tools/prune/__init__.py
delete mode 100644 python/tvm/contrib/msc/framework/tvm/tools/prune/pruner.py
delete mode 100644
python/tvm/contrib/msc/framework/tvm/tools/quantize/__init__.py
delete mode 100644
python/tvm/contrib/msc/framework/tvm/tools/quantize/method.py
delete mode 100644
python/tvm/contrib/msc/framework/tvm/tools/quantize/quantizer.py
delete mode 100644 python/tvm/contrib/msc/framework/tvm/tools/track/__init__.py
delete mode 100644 python/tvm/contrib/msc/framework/tvm/tools/track/tracker.py
delete mode 100644 python/tvm/contrib/msc/pipeline/__init__.py
delete mode 100644 python/tvm/contrib/msc/pipeline/manager.py
delete mode 100644 python/tvm/relax/backend/utils.py
delete mode 100644 python/tvm/relax/frontend/nn/exporter.py
delete mode 100644 python/tvm/relax/frontend/nn/extern.py
delete mode 100644 python/tvm/relax/transform/attach_external_modules.py
delete mode 100644 src/relax/distributed/transform/lower_distir.cc
delete mode 100644
src/relax/distributed/transform/lower_global_view_to_local_view.cc
delete mode 100644 src/relax/op/distributed/ccl.cc
delete mode 100644 src/relax/transform/convert_dataflow.cc
delete mode 100644 src/relax/transform/expand_tuple_arguments.cc
delete mode 100644 src/relax/transform/inline_functions.cc
delete mode 100644 src/relax/transform/remove_unused_outputs.cc
delete mode 100644 src/relax/transform/remove_unused_parameters.cc
create mode 100644 src/runtime/contrib/cutlass/moe_compute_rows.cu
create mode 100644 src/runtime/contrib/cutlass/moe_gemm.cc
create mode 100644 src/runtime/contrib/vllm/attention_kernels.cu
create mode 100644 src/runtime/contrib/vllm/cache_alloc.cc
create mode 100644 src/runtime/contrib/vllm/cache_kernels.cu
create mode 100644 src/runtime/contrib/vllm/dtype_float16.h
rename {include/tvm => src}/runtime/disco/builtin.h (78%)
delete mode 100644 src/runtime/disco/disco_worker_thread.h
rename src/runtime/disco/{disco_worker.cc => worker.cc} (97%)
rename include/tvm/runtime/disco/disco_worker.h => src/runtime/disco/worker.h
(60%)
rename {include/tvm => src}/runtime/relax_vm/ndarray_cache_support.h (77%)
delete mode 100644 tests/python/contrib/test_ccache.py
delete mode 100644 tests/python/contrib/test_msc/test_manager.py
delete mode 100644 tests/python/contrib/test_msc/test_tools.py
delete mode 100644 tests/python/dlight/test_primitives.py
delete mode 100644
tests/python/relax/distributed/test_distributed_transform_lower_distir.py
delete mode 100644
tests/python/relax/distributed/test_distributed_transform_lower_global_to_local_view.py
delete mode 100644 tests/python/relax/frontend_nn_extern_module.cc
create mode 100644 tests/python/relax/test_contrib_vllm.py
delete mode 100644 tests/python/relax/test_frontend_nn_debug.py
delete mode 100644 tests/python/relax/test_inline_functions.py
delete mode 100644 tests/python/relax/test_transform_convert_dataflow.py
delete mode 100644 tests/python/relax/test_transform_expand_tuple_args.py
delete mode 100644
tests/python/relax/test_transform_inline_private_functions.py
delete mode 100644 tests/python/relax/test_transform_normalize_global_var.py
delete mode 100644 tests/python/relax/test_transform_remove_unused_outputs.py
delete mode 100644
tests/python/relax/test_transform_remove_unused_parameters.py
