- 10 Mar, 2020 1 commit
-
-
* Add Nick's changes's squashed * Fix frontend compilation * Re-enable Rust CI * Add changes with conflicted badly * Restructure import_module! macro in order to avoid unstable features * Kill old unstable feature enablement * Refactor common to use new APIs * Move the code to stable * Fix warning Co-authored-by: Nick Hynes <nhynes@oasislabs.com>
Jared Roesch committed
-
- 06 Mar, 2020 1 commit
-
-
Co-authored-by: Jon Soifer <jonso@microsoft.com>
Jon Soifer committed
-
- 16 Jan, 2020 1 commit
-
-
This PR introduces more clear naming prefix for C API type codes to avoid conflict with other packages. We also removed TVMArray and TVMType to directly use DLTensor and DLDataType.
Tianqi Chen committed
-
- 03 Dec, 2019 1 commit
-
-
Tianqi Chen committed
-
- 22 Nov, 2019 1 commit
-
-
Zhi committed
-
- 11 Nov, 2019 1 commit
-
-
Previously runtime::Module was supported using shared_ptr. This PR refactors the codebase to use the Object protocol. It will open doors to allow easier interpolation between Object containers and module in the future.
Tianqi Chen committed
-
- 03 Sep, 2019 2 commits
-
-
This reverts commit 224cc243.
Tianqi Chen committed -
As GraphRuntime does not provide control-flow logics, we have to split our model to two parts. While we need to share parameters between them to save memory usage. Solution: 1) add "lazy_init_input" in graph's attributes "attrs": { ... ... "lazy_init_input": [ "list_str", [ "p0" ] ] } 2) allow un-allocated NDArray entry in SetupStorage 3) utilize "set_input_zero_copy" function to set parameters
Yong Sun committed
-
- 29 Aug, 2019 1 commit
-
-
hlu1 committed
-
- 15 Jul, 2019 1 commit
-
-
* Enable set_input_zero_copy in GraphRuntime * Fix LoadParams * Fix * lint * Fix remote context issue * Fix * Remove LOG * Remove unused variables * Add tests * works * More test scenarios * make it simpler * Remove unnecessary changes * Address comments * More comments * Address comments * Fix build
Yinghai Lu committed
-
- 25 Jun, 2019 1 commit
-
-
Summary: In multi-threaded applications where we have multiple inferences on the same model in parallel (consider e.g. a TTS system handling multiple requests), it can be useful to share the parameters of a model amongst these multiple instances. This improves the cache utilization behaviour of the system, as multiple cores can use the same set of weights instead of evicting the identical copies of weights in a shared cache. As the underlying `NDArray` instances in `data_entry_` implement a ref-counted based sharing system, this is a simple modification of the `GraphRuntime::LoadParams` logic to instead copy parameters from an existing GraphRuntime instance. This is a little ugly in that we need both the pre-existing GraphRuntime instance, as well as the 'serialized' params (since we need to know the set of names we should copy), but without imposing additional assumptions (i.e. storing the set of param names in GraphRuntime, and enforcing that shared param names are identical to the parameters set in the preceding `LoadParams` call), this seems unavoidable. Test Plan: Unit test added.
Andrew Tulloch committed
-
- 23 May, 2019 1 commit
-
-
hlu1 committed
-
- 01 May, 2019 1 commit
-
-
* print op names in graph runtime debug * fix lint
Yida Wang committed
-
- 08 Apr, 2019 1 commit
-
-
* [HEADER] ASF header dir=include * [HEADER] ASF Header dir=src * [HEADER] ASF Header -dir=python * [HEADER] ASF header dir=topi * [HEADER] ASF Header dir=nnvm * [HEADER] ASF Header -dir=tutorials * [HEADER] ASF Header dir=tests * [HEADER] ASF Header -dir=docker * fix whitespace * [HEADER] ASF Header -dir=jvm * [HEADER] ASF Header -dir=web * [HEADER] ASF Header --dir=apps * [HEADER] ASF Header --dir=vta * [HEADER] ASF Header -dir=go * temp * [HEADER] ASF Header --dir=rust * [HEADER] Add ASF Header --dir=cmake * [HEADER] ASF Header --dir=docs * [HEADER] Header for Jenkinsfile * [HEADER] ASF Header to toml and md * [HEADER] ASF Header to gradle * Finalize rat cleanup * Fix permission * Fix java test * temporary remove nnvm onnx test
Tianqi Chen committed
-
- 14 Mar, 2019 1 commit
-
-
Siva committed
-
- 12 Mar, 2019 1 commit
-
-
Tianqi Chen committed
-
- 27 Feb, 2019 1 commit
-
-
hlu1 committed
-
- 03 Feb, 2019 1 commit
-
-
Tianqi Chen committed
-
- 14 Dec, 2018 1 commit
-
-
Wei Chen committed
-
- 05 Nov, 2018 1 commit
-
-
Tianqi Chen committed
-
- 15 Oct, 2018 1 commit
-
-
Siju committed
-
- 04 Oct, 2018 2 commits
-
-
Tianqi Chen committed
-
Siju committed
-
- 22 Sep, 2018 1 commit
-
-
Zhi committed
-
- 11 Sep, 2018 1 commit
-
-
Siva committed
-
- 23 Aug, 2018 1 commit
-
-
MORITA Kazutaka committed
-
- 18 Jul, 2018 1 commit
-
-
Tianqi Chen committed
-
- 31 May, 2018 1 commit
-
-
tqchen committed
-
- 27 Mar, 2018 1 commit
-
-
nhynes committed
-
- 10 Mar, 2018 1 commit
-
-
Tianqi Chen committed
-
- 09 Mar, 2018 1 commit
-
-
Tianqi Chen committed
-
- 05 Mar, 2018 1 commit
-
-
nhynes committed
-
- 21 Feb, 2018 1 commit
-
-
Tianqi Chen committed
-
- 13 Feb, 2018 1 commit
-
-
Need to break after executing intended operation (not before).
Siva committed
-
- 28 Jan, 2018 1 commit
-
-
Siva committed
-
- 23 Jan, 2018 1 commit
-
-
The compilation warning is fixed. src/runtime/graph/graph_runtime.cc:392:24: warning: comparison between signed and unsigned integer expressions [-Wsign-compare] CHECK(data_byte_size == size) ~~~~~~~~~~~~~~~^~~~ /mnt/D_DRIVE/work/nnvm_22_Jan/nnvm_latest/tvm/dmlc-core/include/dmlc/logging.h:109:9: note: in definition of macro ‘CHECK’ if (!(x)) \ ^
Siju Samuel committed
-
- 04 Dec, 2017 1 commit
-
-
* Support rank-0 tensor * fix lint
Tianqi Chen committed
-
- 03 Nov, 2017 1 commit
-
-
Tianqi Chen committed
-
- 26 Sep, 2017 1 commit
-
-
Tianqi Chen committed
-
- 25 Sep, 2017 1 commit
-
-
Tianqi Chen committed
-