Tristan Konolige 55bb8b60b7 [Graph Executor, VM] Add end to end benchmarking of models (#8858) ...

Add benchmarking that includes ovearhead of transfering inputs and
outputs to and from the device. This should give an accurate measurement
of the runtime a user would see when using the model. This is
accomplished by adding functions that run from inputs to return values
into the graph executor and the VM.

2021-08-27 14:39:03 -07:00

..

profiling

[PROFILING] Add json output to profiling reports (#8503)

2021-07-24 15:57:40 +09:00

__init__.py

[Codegen] Use "target.build.$TARGET_KIND" for all codegen functions. (#8071)

2021-06-04 10:34:25 -07:00

_ffi_api.py

[REFACTOR][PY][API-Change] Polish tvm.runtime, tvm.runtime.module API update (#4837)

2020-02-07 09:15:08 -08:00

_ffi_node_api.py

[Format] Convert all Python code w/o CI (#6448)

2020-09-11 22:17:24 +09:00

container.py

[RUNTIME] ShapeTuple Container (#8200)

2021-06-10 07:03:15 +08:00

module.py

[GRAPH EXECUTOR,VM] Add benchmarking function to graph executor and vm (#8807)

2021-08-25 20:25:29 -05:00

ndarray.py

[Docs] Prevented docs/1 file from being generated. (#8029)

2021-06-24 10:27:29 -04:00

object_generic.py

[RUNTIME] Move Map into runtime (#7570)

2021-03-03 14:52:54 -08:00

object.py

[FFI] Specifically check handle for recursion during shutdown (#8548)

2021-07-27 08:52:49 -04:00

packed_func.py

[CI] Introduce all platform test for windows/mac/linux. (#6756)

2020-10-25 19:27:29 -04:00

params.py

[RUNTIME] Unify load params interface (#7559)

2021-03-08 21:40:38 -08:00

profiler_vm.py

[PROFILING] Use PAPI to collect hardware performance counters on CPU and CUDA (#7983)

2021-07-13 09:52:44 -07:00

vm.py

[Graph Executor, VM] Add end to end benchmarking of models (#8858)

2021-08-27 14:39:03 -07:00