-
Notifications
You must be signed in to change notification settings - Fork 0
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
PLDI work #24
base: main
Are you sure you want to change the base?
PLDI work #24
Commits on Jan 13, 2022
-
Configuration menu - View commit details
-
Copy full SHA for 8959d68 - Browse repository at this point
Copy the full SHA 8959d68View commit details -
Configuration menu - View commit details
-
Copy full SHA for f9d8c2b - Browse repository at this point
Copy the full SHA f9d8c2bView commit details -
[Fix Bug] fix the bug of pool_impl_nd when computing avgpool_nd whith…
… ceil_mode and count_include_pad are True. (#9835) * Added the offset[i] for getting the correct boundary * Added corresponding test case
Configuration menu - View commit details
-
Copy full SHA for cc9d2f4 - Browse repository at this point
Copy the full SHA cc9d2f4View commit details -
[skip ci] Fix missing pack_lib in Jenkinsfile (#9924)
This was inadvertently removed by #9554 Co-authored-by: driazati <driazati@users.noreply.github.com>
Configuration menu - View commit details
-
Copy full SHA for 2c1ed59 - Browse repository at this point
Copy the full SHA 2c1ed59View commit details -
[Hexagon] Pass SDK information to launcher build for Android (#9902)
Krzysztof Parzyszek authoredJan 13, 2022 Configuration menu - View commit details
-
Copy full SHA for 5f828a6 - Browse repository at this point
Copy the full SHA 5f828a6View commit details -
std::string -> tvm::String for Conv1DAttrs (#9921)
This is necessary to make the Rust bindings work.
Configuration menu - View commit details
-
Copy full SHA for 424821a - Browse repository at this point
Copy the full SHA 424821aView commit details -
[TIR][Schedule] Annotate allows array as annotaton value (#9920)
Co-authored-by: Siyuan Feng <Hzfengsy@sjtu.edu.cn> Co-authored-by: Bohan Hou <32121147+spectrometerHBH@users.noreply.github.com> Co-authored-by: Hongyi Jin <3231950289@qq.com> Co-authored-by: Ruihang Lai <lairuihangdongdong@qq.com> Co-authored-by: Junru Shao <junrushao1994@gmail.com> Co-authored-by: Xiyou Zhou <xiyou@octoml.ai> Co-authored-by: Siyuan Feng <Hzfengsy@sjtu.edu.cn> Co-authored-by: Bohan Hou <32121147+spectrometerHBH@users.noreply.github.com> Co-authored-by: Hongyi Jin <3231950289@qq.com> Co-authored-by: Ruihang Lai <lairuihangdongdong@qq.com> Co-authored-by: Junru Shao <junrushao1994@gmail.com> Co-authored-by: Xiyou Zhou <xiyou@octoml.ai>
Configuration menu - View commit details
-
Copy full SHA for 7485413 - Browse repository at this point
Copy the full SHA 7485413View commit details
Commits on Jan 14, 2022
-
fix icelake target for avx512 and vnni (#9928)
Matthew Brookhart authoredJan 14, 2022 Configuration menu - View commit details
-
Copy full SHA for 46da676 - Browse repository at this point
Copy the full SHA 46da676View commit details -
Configuration menu - View commit details
-
Copy full SHA for 220b122 - Browse repository at this point
Copy the full SHA 220b122View commit details -
Configuration menu - View commit details
-
Copy full SHA for 0a159c4 - Browse repository at this point
Copy the full SHA 0a159c4View commit details -
[CI] Fix pip cache config bug (#9933)
* Update Dockerfile.ci_arm * Update Dockerfile.ci_cpu * Update Dockerfile.ci_gpu * Update Dockerfile.ci_i386 * Update Dockerfile.ci_lint * Update Dockerfile.ci_qemu * Update Dockerfile.ci_wasm
Configuration menu - View commit details
-
Copy full SHA for 670de9b - Browse repository at this point
Copy the full SHA 670de9bView commit details -
Configuration menu - View commit details
-
Copy full SHA for 79c59fe - Browse repository at this point
Copy the full SHA 79c59feView commit details -
[USMP] Hill Climb allocator (#9704)
* [USMP] Hill Climb allocator This PR adds HillClimb allocator "tir.usmp.algo.hill_climb" to the memory allocation algorithm set. Change-Id: Ib7485df93757eb512da040528ec86c920db8d03b * requested changes Change-Id: I6700a24c1608d92f87be7dde33cc24f5de1f7063 * Conda-related linter small fixes Change-Id: I0dac5c6d75ade8f813b077c8708aad59d2722933 * Moved implementation from greedy.h to greedy.cc Change-Id: If8ed159eceef32d3f22b51e0252161d09222eb1e * Integrated into test_tir_usmp_algo.py unit test Added "hill_climb" into test_tir_usmp_algo.py Amended sorting to be consistent with "greedy" family Change-Id: I8e9f5282f15baaab71d6d129aeb9643376b14763
Configuration menu - View commit details
-
Copy full SHA for 89ae603 - Browse repository at this point
Copy the full SHA 89ae603View commit details -
Configuration menu - View commit details
-
Copy full SHA for 4419241 - Browse repository at this point
Copy the full SHA 4419241View commit details -
[Relay/Frontend][TFLite] Change the output shape calculation based on…
… keep_dim option in fully connected (#9840) * Support -> Change the output shape calculation based on keep_dim option * Support -> Change the output shape calculation based on keep_dim option * Support -> Change the output shape calculation based on keep_dim option * Support -> Change the output shape calculation based on keep_dim option * Change the output shape calculation based on keep_dim option in fully connected * TODO : Need to construct a fc op with (keep_num_dims == True) * TODO : Need to construct a fc op with (keep_num_dims == True)
Configuration menu - View commit details
-
Copy full SHA for e7c8141 - Browse repository at this point
Copy the full SHA e7c8141View commit details
Commits on Jan 15, 2022
-
[TIR] Encode conditional accesses info into block read/write regions …
…(#9880) * encode conditional accesses info into block read/write regions * compare ir after simplify
Configuration menu - View commit details
-
Copy full SHA for 6f6fc68 - Browse repository at this point
Copy the full SHA 6f6fc68View commit details -
[Int8] Support cublas on e2e int8 models (also tried cudnn but doesn'…
…t work) (#9898) * fixed int8 dense offload for cublas * support OHWI kernel layout in qnn.conv2d * fixed reduction axis * add cublas int8 qnn test * lint
Configuration menu - View commit details
-
Copy full SHA for b3c6625 - Browse repository at this point
Copy the full SHA b3c6625View commit details -
Configuration menu - View commit details
-
Copy full SHA for 1b1cfb3 - Browse repository at this point
Copy the full SHA 1b1cfb3View commit details -
[ONNX] Fix onnx convtranspose error (#9938)
* fix mix up of channels with conv2d-transpose * add grouped convtranspose tests * turn off groups for non-llvm test
Configuration menu - View commit details
-
Copy full SHA for 84ee90c - Browse repository at this point
Copy the full SHA 84ee90cView commit details -
[Fix] relay onnx frontend bug when [A, B, M, N] * [1, B, N, K] (#9911)
* [Fix] relay onnx frontend bug when [A, B, M, N] * [1, B, N, K] * fix line Co-authored-by: tomoyazhang <tomoyazhang@tencent.com>
Configuration menu - View commit details
-
Copy full SHA for 6eb4ed8 - Browse repository at this point
Copy the full SHA 6eb4ed8View commit details
Commits on Jan 17, 2022
-
[Caffe Frontend] supporting group > 1 cases for Deconv op (#8260)
* [Caffe Frontend] supporting group > 1 cases for Deconv op - Handling group > 1 cases, assuming group == output channels - Simply decomposed into Relay split, conv2d_transposed, and multi-leveled concatenate ops - Added some test cases Signed-off-by: zotanika <zotanika@gmail.com> * [Caffe Frontend] amending a test case for Deconv op Signed-off-by: zotanika <zotanika@gmail.com> * explicit importing tvm.testing * changing split axis to 0, according to PR #9336
Configuration menu - View commit details
-
Copy full SHA for be0677d - Browse repository at this point
Copy the full SHA be0677dView commit details -
[Caffe Frontend] extending Eltwise to handle multiple inputs (#8136)
* [Caffe Frontend] adding Reduction op * reformatting Reduction op test script * reformatting Reduction test script * [Caffe frontend] Reduction op - adding more test cases; handling '0 < axis < num_axes - 1' case to give the result equivalent to Caffe framework - skipping Relay multiplication if coeff is 1 Signed-off-by: zotanika <zotanika@gmail.com> * linting test script * linting * [Caffe Frontend] Supporting multiple grouped(channel-wise) Deconv op * Handling group > 1 cases, assuming group == output channels * Decomposed into Relay split, transposed conv, and multi-leveled concatenation. * Added some test cases. Signed-off-by: zotanika <zotanika@gmail.com> * [Caffe Frontend] supporting variable number of inputs for Eltwise * extra handling of rest inputs for PROD, SUM, MAX operations * extra testcases Signed-off-by: zotanika <zotanika@gmail.com> * formatting fix * [Caffe Frontend] reverting codes related Reduction for splitting PR * Revert "[Caffe Frontend] Supporting multiple grouped(channel-wise) Deconv op" This reverts commit 43e25e552b790ce9a38fdbcfb3ddf2075c253e20. * instant fix against docker format error * instant fix against docker format error * instant fix against docker format error
Configuration menu - View commit details
-
Copy full SHA for 3c8de42 - Browse repository at this point
Copy the full SHA 3c8de42View commit details -
[MetaSchedule] Schedule Rule: Auto Inline (#9943)
Co-authored-by: Junru Shao <junrushao1994@gmail.com> Co-authored-by: Xiyou Zhou <xiyou@octoml.ai> Co-authored-by: Bohan Hou <32121147+spectrometerHBH@users.noreply.github.com> Co-authored-by: Siyuan Feng <Hzfengsy@sjtu.edu.cn> Co-authored-by: Hongyi Jin <3231950289@qq.com> Co-authored-by: Wuwei Lin <wuwei@apache.org> Co-authored-by: Junru Shao <junrushao1994@gmail.com> Co-authored-by: Xiyou Zhou <xiyou@octoml.ai> Co-authored-by: Bohan Hou <32121147+spectrometerHBH@users.noreply.github.com> Co-authored-by: Siyuan Feng <Hzfengsy@sjtu.edu.cn> Co-authored-by: Hongyi Jin <3231950289@qq.com> Co-authored-by: Wuwei Lin <wuwei@apache.org>
Configuration menu - View commit details
-
Copy full SHA for 596333b - Browse repository at this point
Copy the full SHA 596333bView commit details -
[microNPU] Remove remaining UnsupportedLayout checks (#9791)
* [microNPU] Remove remaining UnsupportedLayout checks In #9508 the decision was made to remove the UnsupportedLayout exception and the checks that throw it, this PR is cleaning up some that remained. Change-Id: I83bfe233381b83af886343c9569db753e33f9059 * fix lint Change-Id: I67c1a5371f0b2e51b6cd39435ef4073d8d17af51
Configuration menu - View commit details
-
Copy full SHA for 24bccd2 - Browse repository at this point
Copy the full SHA 24bccd2View commit details -
[microNPU][2c] Add performance modelling to cascader (#9778)
* [microNPU][2c] Initial Performance Model * Added the pre-computed performance modelling per block. * Added the aggregation of cycles given a stripe config. * Implemented the op-specific performance code for conv2d. * Created a DeviceConfig class to hold constant performance related data that is dependent on the accelerator configuration * Added generation of all valid block configs. This is pre-computed and given as an argument when constructing EthosuParts. * Implemented selection of the block config that gives the least amount of data read given a StripeConfig. * Add test guards * Extended block config testing
Configuration menu - View commit details
-
Copy full SHA for 133bb9c - Browse repository at this point
Copy the full SHA 133bb9cView commit details -
[MetaSchedule] random compute location (#9940)
Co-authored-by: Junru Shao <junrushao1994@gmail.com> Co-authored-by: Xiyou Zhou <xiyou@octoml.ai> Co-authored-by: Bohan Hou <32121147+spectrometerHBH@users.noreply.github.com> Co-authored-by: Ruihang Lai <lairuihangdongdong@qq.com> Co-authored-by: Hongyi Jin <3231950289@qq.com> Co-authored-by: Wuwei Lin <wuwei@apache.org> Co-authored-by: Junru Shao <junrushao1994@gmail.com> Co-authored-by: Xiyou Zhou <xiyou@octoml.ai> Co-authored-by: Bohan Hou <32121147+spectrometerHBH@users.noreply.github.com> Co-authored-by: Ruihang Lai <lairuihangdongdong@qq.com> Co-authored-by: Hongyi Jin <3231950289@qq.com> Co-authored-by: Wuwei Lin <wuwei@apache.org>
Configuration menu - View commit details
-
Copy full SHA for 77c66f0 - Browse repository at this point
Copy the full SHA 77c66f0View commit details -
Configuration menu - View commit details
-
Copy full SHA for 1e5373f - Browse repository at this point
Copy the full SHA 1e5373fView commit details
Commits on Jan 18, 2022
-
[CUDNN] Refactor descriptor initialization, remove `cudnn.conv.output…
…_shape_from_cudnn` (#9948) * Introduce SetConvdescriptors to refactor cudnn/conv_forward.cc * more refactor * remove cudnn get output * cpplint
Configuration menu - View commit details
-
Copy full SHA for 211291f - Browse repository at this point
Copy the full SHA 211291fView commit details -
[microNPU] Add support for scalar values (#9794)
* [microNPU] Add support for scalar values PR #9515 enabled support for scalar constants, but didn't consider the case of a scalar value where the underlying constant data does not have a shape i.e. `constant.shape == []`. See the test case for a visual differece when the scalar value is 1. Change-Id: Id7a238cb5bf999dd5a8428c097202f9fb940a5f0 * Fix failing test by removing constant Before this PR scalar constants were handled differently so this test was able to pass. Now that scalar constants are handled in the same manner as tensor constants, the test fails since unexpected tir is produced in the compilation pipeline. Since the relay used in this test case is not expected to be produced by higher levels of the compiler, removing this constant for now. Change-Id: I4ea5155778809041339e6faac05af3f72c3e3ea5 * clean up finding tensor from inputs Change-Id: Ideccf84f8c9149148ff23e2406229cf637c982a3
Configuration menu - View commit details
-
Copy full SHA for 364e2db - Browse repository at this point
Copy the full SHA 364e2dbView commit details -
Configuration menu - View commit details
-
Copy full SHA for 31de5bc - Browse repository at this point
Copy the full SHA 31de5bcView commit details -
Enable NPU and CMSIS in ci_qemu (#9957)
These are required for running the demos under ci_qemu in combination with Zephyr
Configuration menu - View commit details
-
Copy full SHA for 4f29562 - Browse repository at this point
Copy the full SHA 4f29562View commit details -
[Runtime][Pipeline executor] Global parameters group name and runtime…
… modules parameters map. (#9846) * [Runtime][Pipeline executor] Global parameters group name and runtime modules parameters map. Solution: To support on the fly parameters setting for each runtime module in pipeline executor, we create a feature that use global parameters group name to map the runtime module parameter, after such map relation get created user can do the on the fly parameters setting by using the parameters group name. trigger build. fix ut issue. polish comments. Update python/tvm/contrib/pipeline_executor.py Co-authored-by: Cody Yu <comaniac0422@gmail.com> Update python/tvm/contrib/pipeline_executor.py Co-authored-by: Cody Yu <comaniac0422@gmail.com> Update python/tvm/contrib/pipeline_executor.py Co-authored-by: Cody Yu <comaniac0422@gmail.com> Update python/tvm/contrib/pipeline_executor.py Co-authored-by: Cody Yu <comaniac0422@gmail.com> Update src/runtime/pipeline/pipeline_executor.h Co-authored-by: Cody Yu <comaniac0422@gmail.com> Update src/runtime/pipeline/pipeline_struct.h Co-authored-by: Cody Yu <comaniac0422@gmail.com> Update python/tvm/contrib/pipeline_executor.py Co-authored-by: Cody Yu <comaniac0422@gmail.com> address review comments. * Update python/tvm/contrib/pipeline_executor.py Co-authored-by: Cody Yu <comaniac0422@gmail.com> * fix plint issue. Co-authored-by: Cody Yu <comaniac0422@gmail.com>
Configuration menu - View commit details
-
Copy full SHA for b1bd18e - Browse repository at this point
Copy the full SHA b1bd18eView commit details
Commits on Jan 19, 2022
-
* jenkinsfile and one test * formatting * swtich to proper repo for docker * fix missing - with _ * jostle * upgrade to latest images * jenkinsfile and one test * formatting * swtich to proper repo for docker * fix missing - with _ * upgrade to latest images * jostle ci * update with official images * jostle ci
Configuration menu - View commit details
-
Copy full SHA for 904b4ae - Browse repository at this point
Copy the full SHA 904b4aeView commit details -
[TOPI,x86] Improve performance on int8 conv2d on x86 (#9966)
Appended fused operations in cov2d for int8 were computed in a separate loop from the main conv2d computation: ``` for i in ... parallel for j in ... accumulator = 0 for k in .. vectorized_multiply_add(accumulator, data, kernel) out = accumulator for k in .. out = out + fused subsequent ops ``` This patch moves the fused ops one more loop nesting inwards to get ``` for i in ... parallel for j in ... accumulator = 0 for k in .. vectorized_multiply_add(accumulator, data, kernel) out = accumulator + fused subsequent ops ``` On quantized mobilenetv2, this results in approximately a 30% speedup.
Tristan Konolige authoredJan 19, 2022 Configuration menu - View commit details
-
Copy full SHA for 19717aa - Browse repository at this point
Copy the full SHA 19717aaView commit details -
[Hexagon] Return pathlib.Path from get_hexagon_rpc_path() (#9969)
Type annotations don't do anything, the type conversion needs to be explicit.
Krzysztof Parzyszek authoredJan 19, 2022 Configuration menu - View commit details
-
Copy full SHA for da3b63e - Browse repository at this point
Copy the full SHA da3b63eView commit details -
[Hexagon] Add missing #include <iterator> (#9968)
This fixes compilation error with libstdc++.
Krzysztof Parzyszek authoredJan 19, 2022 Configuration menu - View commit details
-
Copy full SHA for 928be03 - Browse repository at this point
Copy the full SHA 928be03View commit details -
[Doc][Fix] Fix qnn op parameters hint order (#9622)
As the following parameters are both Expr. ``` zero_point : tvm.relay.Expr scale : tvm.relay.Expr ``` It's really get me confused when I followed the python arg hints to create a relay and without success.
Configuration menu - View commit details
-
Copy full SHA for 6d68184 - Browse repository at this point
Copy the full SHA 6d68184View commit details -
Propagate ssh-agent authentication socket (#9926)
In case that SSH_AUTH_SOCK is defined, two items will be added to the docker run command: 1) A propageted ssh authentication socket value , to support an underlying ssh calls inside the running contianer. 2) A mounted volume for ssh channel. Co-authored-by: Samuel Panijel <samuel.panijel@arm.com>
Configuration menu - View commit details
-
Copy full SHA for ac1a43b - Browse repository at this point
Copy the full SHA ac1a43bView commit details -
[TIR][USMP] Integrating USMP to AoT Executor (#9565)
This commit integrates USMP with the AoT executor codegen. Additionally, this commit introduces two PassContext options to disable_usmp and disable_storage_rewrite. Moved PrintType from codegen_c.cc to codegen_source_base.cc to be accessible by source_module.cc Moved runtime::metadata to be ExecutorCodegeMetadata as it contains metadata produced by ExecutorCodegen for actual code generation (not a runtime component).
Configuration menu - View commit details
-
Copy full SHA for c3ace20 - Browse repository at this point
Copy the full SHA c3ace20View commit details -
Disallow copy to/from external HexagonBuffer (#9930)
* Disallow copy to/from external HexagonBuffer * change nbytes -> allocation_nbytes for clarity * retrigger ci
Configuration menu - View commit details
-
Copy full SHA for f1501d0 - Browse repository at this point
Copy the full SHA f1501d0View commit details -
[Fix] Fix flaky test of #9952 (#9958)
* fix to stablize the var orders when solve bounds in region analysis * change to std::find_if since num of vars is generally small
Configuration menu - View commit details
-
Copy full SHA for 611b430 - Browse repository at this point
Copy the full SHA 611b430View commit details -
Add contribute page about CI (#9906)
* Add contribute page about CI This adds some docs with a description of the TVM CI and some usage instructions to both make contributing more friendly and educate existing developers about how CI runs. Bikeshedding on content is welcome Note: The TODOs are blocked on some other PRs and will be done before landing * docker instructions * Comments * Rebase Co-authored-by: driazati <driazati@users.noreply.github.com>
Configuration menu - View commit details
-
Copy full SHA for 1351ede - Browse repository at this point
Copy the full SHA 1351edeView commit details -
Configuration menu - View commit details
-
Copy full SHA for 6286ac1 - Browse repository at this point
Copy the full SHA 6286ac1View commit details -
Configuration menu - View commit details
-
Copy full SHA for a9b1d5b - Browse repository at this point
Copy the full SHA a9b1d5bView commit details -
[Relay] Add
conv2d_backward_weight
op (without topi) (#9954)* python plumbing * add cpp def * legalize worked * clean up * layout conversion doesnt work * extract wgrad body * fix convert layout * black * fix kernel size * revert irrelevant change * add doc, clarify the meanings of parameters * update layout convert * test passed * fixed layout conversion * update convert layout * remove print * remove layout convert for now * minor fix * removed unused import * add wgrad python reference * add test stub * add doc * test other stride and pad * tweak * more pylint filter * fix typo in doc * swap arg order (data, grad) to be consistent with conv2d_transpose(dgrad)
Configuration menu - View commit details
-
Copy full SHA for fd5915a - Browse repository at this point
Copy the full SHA fd5915aView commit details -
[MetaSchedule] Schedule Rule: Add RFactor (#9975)
* add rfactor * format * fix ci
Configuration menu - View commit details
-
Copy full SHA for f9171f1 - Browse repository at this point
Copy the full SHA f9171f1View commit details -
Add Action to add cc'ed people as reviewers (#9934)
* Add action to label mergeable PRs Developers often have to ping a committer once their PRs are both passing in CI and are approved. This helps facilitate this process by marking such PRs with a label `ready-for-merge` so committers can easily filter for outstanding PRs that need attention. * Fix lint and add tests * Add Action to add cc'ed people as reviewers This provides a mechanism for non-triager/reviewer/committer PR authors to request reviews through GitHub. Anyone that is referenced by `cc @username` in a PR body will be added as a reviewer (GitHub will limit the reviewers to those with actual permissions to leave reviews so the script to add can be simple). * remove merge bot stuff * Fix target triggers Co-authored-by: driazati <driazati@users.noreply.github.com>
Configuration menu - View commit details
-
Copy full SHA for bae144c - Browse repository at this point
Copy the full SHA bae144cView commit details -
Add runtime.ModuleGetFormat method enabling export of BYOC generated …
…sources which require a .cpp/.cc file extension (#9243) * Allow export of C++ kernels using correct file extension * [WIP] Set module_key=c for CSourceCrtMetadataModuleNode to temporarily fix failing tests I realized that the module format `cc` is currently already used by the `CSourceCrtMetadataModuleNode` declared in `src/target/source/source_module.cc`. This needs to be discussed first to decide if either the module_key should be changed or the test cases expecting the systemlib kernel (e.g. `default_lib0.c`) to have a `.c` extension. * Update Makefiles used by tests/python/relay/aot/ to support C++ file extensions AOT: Add c++ support to aot_test.mk AOT: Add c++ support to corstone300.mk * Add missing definition of GetFormat to cmsisnn and ethosn codegens (WIP) * Resolve PR comments * lint python/tvm/runtime/module.py * fix EthosUModuleNode for CI * Fix: detect empty module.format * Add error message to assertion * Lint python/tvm/runtime/module.py
Configuration menu - View commit details
-
Copy full SHA for cc5382e - Browse repository at this point
Copy the full SHA cc5382eView commit details -
* finish rpc and shape_dict in tut * added more to rpc * tutorial edits * added tutorial to docs in howto * accidentally had two copies of tutorial * Update gallery/how_to/use_tvms_python_api/tvmc_python.py Co-authored-by: Leandro Nunes <leandro.nunes@arm.com> * Update gallery/how_to/use_tvms_python_api/tvmc_python.py Co-authored-by: Leandro Nunes <leandro.nunes@arm.com> * Update gallery/how_to/use_tvms_python_api/tvmc_python.py Co-authored-by: Leandro Nunes <leandro.nunes@arm.com> * Update gallery/how_to/use_tvms_python_api/tvmc_python.py Co-authored-by: Leandro Nunes <leandro.nunes@arm.com> * Apply suggestions from code review Co-authored-by: Leandro Nunes <leandro.nunes@arm.com> * Update gallery/how_to/use_tvms_python_api/tvmc_python.py Co-authored-by: Leandro Nunes <leandro.nunes@arm.com> * Update gallery/how_to/use_tvms_python_api/tvmc_python.py Co-authored-by: Leandro Nunes <leandro.nunes@arm.com> * added Leandro's suggestions * added example model at top * added example model, blacked it * trying to get docs to build * underline too short for title * forgot Jetson info, added Chris H comments * reformatting text * black * hitting code block issue, trying to debug * added spaces after the python codeblock * black * changing formatting * touching up more edits' * more touchups * changed location of file to tutorial section * changing doc location * broke the order of the docs somehow * fixed it yayy * added additional indentation * black'd Co-authored-by: CircleSpin <jocelyn@pop-os.localdomain> Co-authored-by: Leandro Nunes <leandro.nunes@arm.com>
Configuration menu - View commit details
-
Copy full SHA for 14d0187 - Browse repository at this point
Copy the full SHA 14d0187View commit details
Commits on Jan 20, 2022
-
Configuration menu - View commit details
-
Copy full SHA for 73aa415 - Browse repository at this point
Copy the full SHA 73aa415View commit details -
[microNPU][2d] Add more Part matchers to cascader (#9785)
* [microNPU][2d] Add more Part matchers for the cascader Adds Part matchers for ethosu_depthwise_conv2d, ethosu_pooling and ethosu_binary_elementwise. Also adds additional testing for the CascaderGraph creation. Co-authored-by: Jacob Bohlin <jacob.bohlin@arm.com> * Extended testing for block config * Add test guards Co-authored-by: Matthew Barrett <matthew.barrett@arm.com>
Configuration menu - View commit details
-
Copy full SHA for bcdc345 - Browse repository at this point
Copy the full SHA bcdc345View commit details -
Configuration menu - View commit details
-
Copy full SHA for 589fc01 - Browse repository at this point
Copy the full SHA 589fc01View commit details -
[microNPU] Move optimization passes to be a module pass and ensure th…
…ey (#9831) are running Moves LayoutOptimizer and LUTOptimizer passes to be a module pass, rather than a function pass. This is because it was found that these passes were not running in the NPU compilation flow. In addition, a test for both LayoutOptimizer and LUTOptimizer has been added to check that the passes are running in the compilation pipeline of the NPU. Change-Id: I5145c6f02eeb0daea3cdba56198e0804ec32f351
Configuration menu - View commit details
-
Copy full SHA for e390d9e - Browse repository at this point
Copy the full SHA e390d9eView commit details -
[CI] Fix Rust path and remove wasmtime from ci_qemu (#10001)
This fixes the Rust path to ensure `cargo` is accessible in the container. As ci_qemu is targetted at microTVM it likely won't make use of wasmtime as a dependency - it's used instead for the JS and WASM standalone applications as far as I can see.
Configuration menu - View commit details
-
Copy full SHA for 099ebaa - Browse repository at this point
Copy the full SHA 099ebaaView commit details
Commits on Jan 21, 2022
-
[Relay] Fix a bug in tensor_array_scatter (#6890)
* [Relay] Fix a bug in tensor_array_scatter tensor_array_scatter constructs helper functions according to dtype and shape of element. When there are multiple scatter operations with same dtype and element shape but different indicies_shape, there will be name conflict in prelude. * Refine get_name
Configuration menu - View commit details
-
Copy full SHA for a427efb - Browse repository at this point
Copy the full SHA a427efbView commit details -
* Fix typos. * Missed funtion -> function.
Configuration menu - View commit details
-
Copy full SHA for e05a62b - Browse repository at this point
Copy the full SHA e05a62bView commit details -
Make cc bot skip errors (#9988)
* [skip ci] Make cc bot skip errors This adds some better logging and ignores errors (this job shouldn't ever show up as a PR failure) so we can diagnose things like https://github.com/apache/tvm/runs/4873810315?check_suite_focus=true * Submit cc'ed reviewers one at a time Co-authored-by: driazati <driazati@users.noreply.github.com>
Configuration menu - View commit details
-
Copy full SHA for 2426749 - Browse repository at this point
Copy the full SHA 2426749View commit details -
Don't use std::move in WithFields (#10009)
* Don't use std::move in WithFields * lint
Configuration menu - View commit details
-
Copy full SHA for 11a84c1 - Browse repository at this point
Copy the full SHA 11a84c1View commit details -
[LLVM][Hexagon] Revert LLVM header change for version 14 (#10006)
* Revert LLVM header change * Trigger
Configuration menu - View commit details
-
Copy full SHA for 2a91f0d - Browse repository at this point
Copy the full SHA 2a91f0dView commit details -
[MetaSchedule] Post Processor: Rewrite Reduction Block (#10013)
Co-authored-by: Junru Shao <junrushao1994@gmail.com> Co-authored-by: Xiyou Zhou <xiyou@octoml.ai> Co-authored-by: Bohan Hou <32121147+spectrometerHBH@users.noreply.github.com> Co-authored-by: Siyuan Feng <Hzfengsy@sjtu.edu.cn> Co-authored-by: Hongyi Jin <3231950289@qq.com> Co-authored-by: Wuwei Lin <wuwei@apache.org> Co-authored-by: Junru Shao <junrushao1994@gmail.com> Co-authored-by: Xiyou Zhou <xiyou@octoml.ai> Co-authored-by: Bohan Hou <32121147+spectrometerHBH@users.noreply.github.com> Co-authored-by: Siyuan Feng <Hzfengsy@sjtu.edu.cn> Co-authored-by: Hongyi Jin <3231950289@qq.com> Co-authored-by: Wuwei Lin <wuwei@apache.org>
Configuration menu - View commit details
-
Copy full SHA for d97274c - Browse repository at this point
Copy the full SHA d97274cView commit details -
[frontend][keras] Add support for TimeDistributed (#7006)
* First pass on modifying Keras importer to handle TimeDistributed * Use squeeze inside TimeDistributed, add tests * linter fixes * More linting * Even more linting * Fix unused argument annotations * Forgot one pylint annotation * Forgot to set up data layout in _convert_activation * Decouple data_layout from etab * Linting fix * Forgot to set data_layout argument * Missed an etab.data_format, also test_conv1d was not in the test file's main * Rebase fixes * Linting fix * _convert_lambda needs a data layout argument too * linting fix too * Lint the test file too * Redundant variables * Simplify further * Another simplification Co-authored-by: Steven Lyubomirsky <slyubomirsky@octoml.ai>
Configuration menu - View commit details
-
Copy full SHA for 25c8f4c - Browse repository at this point
Copy the full SHA 25c8f4cView commit details -
Auto-discover C/C++ compiler instead of hardcoding g++ (#10007)
Some platforms (e.g. FreeBSD) use clang as the default OS compiler, and there is no g++.
Krzysztof Parzyszek authoredJan 21, 2022 Configuration menu - View commit details
-
Copy full SHA for 751f83b - Browse repository at this point
Copy the full SHA 751f83bView commit details -
[Docker] Relax name check (#10011)
Fix a issue that user name like aaa.bb can't be added to docker container
Configuration menu - View commit details
-
Copy full SHA for 81b66e6 - Browse repository at this point
Copy the full SHA 81b66e6View commit details -
[MetaSchedule] Schedule Rule: Cross Thread Reduction (#9994)
Co-authored-by: Junru Shao <junrushao1994@gmail.com> Co-authored-by: Xiyou Zhou <xiyou@octoml.ai> Co-authored-by: Bohan Hou <32121147+spectrometerHBH@users.noreply.github.com> Co-authored-by: Siyuan Feng <Hzfengsy@sjtu.edu.cn> Co-authored-by: Ruihang Lai <lairuihangdongdong@qq.com> Co-authored-by: Wuwei Lin <wuwei@apache.org>
Configuration menu - View commit details
-
Copy full SHA for 1ac01b4 - Browse repository at this point
Copy the full SHA 1ac01b4View commit details
Commits on Jan 22, 2022
-
[TOPI,CUDA] Don't enable cudnn conv2d kernel if is not supported (#10…
…021) * [TOPI,CUDA] Don't enable cudnn conv2d kernel if is not supported Specifically, check that layout is not NCHW if datatype is int8. * remove all conv2d_cudnn int8 support
Tristan Konolige authoredJan 22, 2022 Configuration menu - View commit details
-
Copy full SHA for e9ee73f - Browse repository at this point
Copy the full SHA e9ee73fView commit details -
[BugFix][TIR] Fix cross-thread reduction when single reduction loop w…
…ith predicate (#10016)
Configuration menu - View commit details
-
Copy full SHA for 89fa241 - Browse repository at this point
Copy the full SHA 89fa241View commit details -
Add user-configurable backtrace limit (#10025)
A spin off of #9872, this adds an env variable `TVM_BACKTRACE_LIMIT` which can be set to an integer to limit the frames printed out on errors. This can make it easier to run interactive TVM scripts with errors since the stack traces are often long (70+ frames). ```bash export TVM_BACKTRACE_LIMIT=5 python some_code_with_an_error.py ``` cc @tkonolige Co-authored-by: driazati <driazati@users.noreply.github.com>
Configuration menu - View commit details
-
Copy full SHA for 9a6423c - Browse repository at this point
Copy the full SHA 9a6423cView commit details -
[MetaSchedule] disallow_dynamic_loop (#9997)
* [MetaSchedule] disallow_dynamic_loop Co-authored-by: Junru Shao <junrushao1994@gmail.com> Co-authored-by: Xiyou Zhou <xiyou@octoml.ai> Co-authored-by: Bohan Hou <32121147+spectrometerHBH@users.noreply.github.com> Co-authored-by: Ruihang Lai <lairuihangdongdong@qq.com> Co-authored-by: Hongyi Jin <3231950289@qq.com> Co-authored-by: Wuwei Lin <wuwei@apache.org> * Update src/meta_schedule/postproc/disallow_dynamic_loop.cc Co-authored-by: Ruihang Lai <lairuihangdongdong@qq.com> Co-authored-by: Junru Shao <junrushao1994@gmail.com> Co-authored-by: Xiyou Zhou <xiyou@octoml.ai> Co-authored-by: Bohan Hou <32121147+spectrometerHBH@users.noreply.github.com> Co-authored-by: Ruihang Lai <lairuihangdongdong@qq.com> Co-authored-by: Hongyi Jin <3231950289@qq.com> Co-authored-by: Wuwei Lin <wuwei@apache.org>
Configuration menu - View commit details
-
Copy full SHA for 64f2939 - Browse repository at this point
Copy the full SHA 64f2939View commit details -
[CUDNN] Support gradient kernels (#9986)
* Dgrad nchw, nhwc, fp16 working commit 426e5dca446a27da49270f45171b58f1bfa21fa9 Author: Masahiro Masuda <masahi129@gmail.com> Date: Tue Jan 18 11:48:53 2022 +0900 black commit 211a58b80f4d0f0b5b0230720e41f35e50cb1eaf Author: Masahiro Masuda <masahi129@gmail.com> Date: Tue Jan 18 11:43:52 2022 +0900 fp16 also works commit c2a34d473b063873628bff00e51a44cd8e4d0e4f Author: Masahiro Masuda <masahi129@gmail.com> Date: Tue Jan 18 11:36:36 2022 +0900 nhwc test also worked commit c0609ab147fef30c230a94d16b6c1ba35f7dd9c0 Author: Masahiro Masuda <masahi129@gmail.com> Date: Tue Jan 18 11:21:23 2022 +0900 nchw test worked commit 2bf68c72763708151e9f49f09916a210b2547be8 Author: Masahiro Masuda <masahi129@gmail.com> Date: Tue Jan 18 10:41:35 2022 +0900 add test stub commit c86b1288d5e371f12cba4e1b1866966cb9264401 Author: Masahiro Masuda <masahi129@gmail.com> Date: Tue Jan 18 10:32:09 2022 +0900 add python definition stub commit 3166952f9673376801bf4b5b39eeb6f89452f30a Author: Masahiro Masuda <masahi129@gmail.com> Date: Tue Jan 18 06:57:18 2022 +0900 bwd filter compiled commit e311ba3d05c5f9424ecb952cb5a520ce81a0828a Author: Masahiro Masuda <masahi129@gmail.com> Date: Tue Jan 18 06:27:55 2022 +0900 dgrad compiled commit 47f35beb5eeeb7cbf9f6ec7cf8f5c80c65e8da46 Author: Masahiro Masuda <masahi129@gmail.com> Date: Tue Jan 18 06:16:43 2022 +0900 add dgrad stub commit ebed032d15b1c3895f541c46ce5d80b6dd769034 Author: Masahiro Masuda <masahi129@gmail.com> Date: Mon Jan 17 17:01:56 2022 +0900 cpplint commit 834f54a8c13512130e7d91ca0f54268dc06c5481 Author: Masahiro Masuda <masahi129@gmail.com> Date: Mon Jan 17 16:55:58 2022 +0900 remove cudnn get output commit dcbd9c95fdb8ffef9db9c2350430b270461a31c3 Author: Masahiro Masuda <masahi129@gmail.com> Date: Mon Jan 17 16:28:07 2022 +0900 more refactor commit 146464e8496fff972bdb1687c4e9d432fe3278d5 Author: Masahiro Masuda <masahi129@gmail.com> Date: Mon Jan 17 15:57:35 2022 +0900 Introduce SetConvdescriptors to refactor cudnn/conv_forward.cc * add python function for cudnn wgrad * adding wgrad test * black * wgrad nchw and nhwc worked * remove bwd algo name stuff * compute output shape properly * swap arg order in wgrad * add kernel size arg in test * black * cleanup * more fix * fix dgrad test * support running relay conv2d_backward_weight directly with cudnn * black * refactor reference function to support nhwc * removed unused function * lint * enable offloading conv2d_transpose to cudnn dgrad * relax tol * name fix, remove print
Configuration menu - View commit details
-
Copy full SHA for d35b858 - Browse repository at this point
Copy the full SHA d35b858View commit details
Commits on Jan 23, 2022
-
Configuration menu - View commit details
-
Copy full SHA for 7bfb11b - Browse repository at this point
Copy the full SHA 7bfb11bView commit details -
[MetaSchedule] Mutator: Mutate compute location (#10028)
Co-authored-by: Junru Shao <junrushao1994@gmail.com> Co-authored-by: Xiyou Zhou <xiyou@octoml.ai> Co-authored-by: Bohan Hou <32121147+spectrometerHBH@users.noreply.github.com> Co-authored-by: Ruihang Lai <lairuihangdongdong@qq.com> Co-authored-by: Hongyi Jin <3231950289@qq.com> Co-authored-by: Wuwei Lin <wuwei@apache.org> Co-authored-by: Junru Shao <junrushao1994@gmail.com> Co-authored-by: Xiyou Zhou <xiyou@octoml.ai> Co-authored-by: Bohan Hou <32121147+spectrometerHBH@users.noreply.github.com> Co-authored-by: Ruihang Lai <lairuihangdongdong@qq.com> Co-authored-by: Hongyi Jin <3231950289@qq.com> Co-authored-by: Wuwei Lin <wuwei@apache.org>
Configuration menu - View commit details
-
Copy full SHA for fc1814e - Browse repository at this point
Copy the full SHA fc1814eView commit details -
[MetaSchedule] Post Processor: Rewrite Unbound Block (#10027)
Co-authored-by: Junru Shao <junrushao1994@gmail.com> Co-authored-by: Xiyou Zhou <xiyou@octoml.ai> Co-authored-by: Bohan Hou <32121147+spectrometerHBH@users.noreply.github.com> Co-authored-by: Siyuan Feng <Hzfengsy@sjtu.edu.cn> Co-authored-by: Hongyi Jin <3231950289@qq.com> Co-authored-by: Wuwei Lin <wuwei@apache.org> Co-authored-by: Junru Shao <junrushao1994@gmail.com> Co-authored-by: Xiyou Zhou <xiyou@octoml.ai> Co-authored-by: Bohan Hou <32121147+spectrometerHBH@users.noreply.github.com> Co-authored-by: Siyuan Feng <Hzfengsy@sjtu.edu.cn> Co-authored-by: Hongyi Jin <3231950289@qq.com> Co-authored-by: Wuwei Lin <wuwei@apache.org>
Configuration menu - View commit details
-
Copy full SHA for cc67040 - Browse repository at this point
Copy the full SHA cc67040View commit details -
[MetaSchedule] Schedule Rule: Parallelize-Vectorize-Unroll (#10033)
Co-authored-by: Junru Shao <junrushao1994@gmail.com> Co-authored-by: Xiyou Zhou <xiyou@octoml.ai> Co-authored-by: Bohan Hou <32121147+spectrometerHBH@users.noreply.github.com> Co-authored-by: Siyuan Feng <Hzfengsy@sjtu.edu.cn> Co-authored-by: Hongyi Jin <3231950289@qq.com> Co-authored-by: Wuwei Lin <wuwei@apache.org> Co-authored-by: Junru Shao <junrushao1994@gmail.com> Co-authored-by: Xiyou Zhou <xiyou@octoml.ai> Co-authored-by: Bohan Hou <32121147+spectrometerHBH@users.noreply.github.com> Co-authored-by: Siyuan Feng <Hzfengsy@sjtu.edu.cn> Co-authored-by: Hongyi Jin <3231950289@qq.com> Co-authored-by: Wuwei Lin <wuwei@apache.org>
Configuration menu - View commit details
-
Copy full SHA for de01c3e - Browse repository at this point
Copy the full SHA de01c3eView commit details
Commits on Jan 24, 2022
-
[microNPU] Add support for requantize (#9910)
* [microNPU] Add support for requantize Adds support for stand-alone requantize operation which is legalized to an identity operation on the NPU. Change-Id: Ie2450c5fc72f405eddf517593236074aa4716c3b * fix concatenate tests failing due to not being bit exact Since requantize is now offloaded, concatenate tests were failing due a reference not being used. Change-Id: I44b26b5daecfefb776ca19e6646f3690f5570f52 * test multiple requantize offload Change-Id: I60a3283461a7a7083c05289e84f570698388077b * address comments Change-Id: I7196a0fa468eb7c6a96f2b8a68f3a2dcf5a5693c
Configuration menu - View commit details
-
Copy full SHA for 74a2fa8 - Browse repository at this point
Copy the full SHA 74a2fa8View commit details -
Configuration menu - View commit details
-
Copy full SHA for d066441 - Browse repository at this point
Copy the full SHA d066441View commit details -
[CMSIS-NN] Update microNPU demo to include offloading to CMSIS-NN (#9…
…979) * [CMSIS-NN] Update microNPU demo to include offloading to CMSIS-NN Change-Id: I6a3ba9db3e3cb2bd7c10383ebd52f9a1cdad74d0 * [CMSIS-NN] Update microNPU demo to include offloading to CMSIS-NN * Addressing comments Change-Id: I98fcdf95bf408700968827e1abd084a916b3b21c * [CMSIS-NN] Update microNPU demo to include offloading to CMSIS-NN * Addressing comments * Remove build folder before running demo to address #10020 Change-Id: Ifa7ad3ff431f427f8afb8b3c9f06711b3b59ad62 * Correctly filter tvmc Targets Fixed logic to check for >2 TVM Target to be based on none-hybrid Targets only Co-authored-by: Chris Sidebottom <chris.sidebottom@arm.com>
Configuration menu - View commit details
-
Copy full SHA for 65b4b09 - Browse repository at this point
Copy the full SHA 65b4b09View commit details -
Configuration menu - View commit details
-
Copy full SHA for 6f2b35f - Browse repository at this point
Copy the full SHA 6f2b35fView commit details -
[Hexagon] Do not auto-build apps when building TVM (#9970)
* [Hexagon] Do not auto-build apps when building TVM The Hexagon cmakes have recently become unwieldy due to a complex network of dependencies between various automatically built components. This was in large part because of trying to automatically build some apps, which then tried to build TVM runtimes again, but with their own configurations. This patch removes the ability to automatically build any Hexagon- -related apps from the main TVM build. The following cmake options are now deprecated: - `USE_HEXAGON_LAUNCHER` - `USE_HEXAGON_PROXY_RPC` In order to build the binaries needed for HexagonLauncher from tvm.contrib.hexagon: - Build TVM+runtime for x86, with codegen for Hexagon enabled. This can be done via `USE_HEXAGON_DEVICE=sim` or `target`. - Build Android runtime and tvm_rpc with `-DUSE_RPC=ON`, `-DUSE_CPP_RPC=ON`, and `-DUSE_HEXAGON_RPC=ON`. - Build Hexagon runtime with `-DUSE_HEXAGON_RPC=ON`, and `-DBUILD_STATIC_RUNTIME=ON`. * Add README.md * Restart CI * Add optional variable to set output directory
Krzysztof Parzyszek authoredJan 24, 2022 Configuration menu - View commit details
-
Copy full SHA for 73bbfbb - Browse repository at this point
Copy the full SHA 73bbfbbView commit details
Commits on Jan 25, 2022
-
[Runtime][PipelineExecutor] Add Pipeline Executor Interface (#10010)
Adding interfaces into Pipeline Executor to "run", "stop","set input", and "get input" from the pipeline executor, In this patch, we also implemented the "BackendRuntime" structure to wrap the graph runtime interface in order to support pipeline executor interface and implement data copy method. This method is used to transfer data between two backend runtimes.
Configuration menu - View commit details
-
Copy full SHA for 6720d35 - Browse repository at this point
Copy the full SHA 6720d35View commit details
Commits on Jan 26, 2022
-
Configuration menu - View commit details
-
Copy full SHA for 2830c96 - Browse repository at this point
Copy the full SHA 2830c96View commit details -
[CUTLASS] Profile only the largest-possible alignment by default (#10…
…036) * introduce profile_all_alignments option * add profile_all_alignment option to API * wip * fixed dynamic case * black * update gen_gemm too * minor improvement * fix * all tests work * add doc * fixed for sm = 75 case * fix typo * remove unused import * profile_all -> find_first_valid * fix
Configuration menu - View commit details
-
Copy full SHA for 1b9b05e - Browse repository at this point
Copy the full SHA 1b9b05eView commit details -
[Meta Schedule] Add
ApplyHisotryBest
Meta Schedule Context (#10049)* Add ApplyHisotryBest. Co-authored-by: Junru Shao <junrushao1994@gmail.com> Co-authored-by: Bohan Hou <32121147+spectrometerHBH@users.noreply.github.com> Co-authored-by: Ruihang Lai <lairuihangdongdong@qq.com> Co-authored-by: Hongyi Jin <3231950289@qq.com> Co-authored-by: Wuwei Lin <wuwei@apache.org> Co-authored-by: Siyuan Feng <Hzfengsy@sjtu.edu.cn> * Retrigger CI. * Update integration.py Co-authored-by: Junru Shao <junrushao1994@gmail.com> Co-authored-by: Bohan Hou <32121147+spectrometerHBH@users.noreply.github.com> Co-authored-by: Ruihang Lai <lairuihangdongdong@qq.com> Co-authored-by: Hongyi Jin <3231950289@qq.com> Co-authored-by: Wuwei Lin <wuwei@apache.org> Co-authored-by: Siyuan Feng <Hzfengsy@sjtu.edu.cn>
Configuration menu - View commit details
-
Copy full SHA for 94c4e0e - Browse repository at this point
Copy the full SHA 94c4e0eView commit details -
[MetaSchedule] Mutator Rule: Mutate Unroll (#10045)
* mutate-unroll * mutate-unroll
Configuration menu - View commit details
-
Copy full SHA for 88cbf1b - Browse repository at this point
Copy the full SHA 88cbf1bView commit details -
[TIR][Schedule] Blockize and Tensorize (#9871)
* WIP * WIP * WIP * test cases * add examples * lint * Amend co-authors information Co-authored-by: Siyuan Feng <Hzfengsy@sjtu.edu.cn> Co-authored-by: Bohan Hou <32121147+spectrometerHBH@users.noreply.github.com> Co-authored-by: Hongyi Jin <3231950289@qq.com> Co-authored-by: Ruihang Lai <lairuihangdongdong@qq.com> Co-authored-by: Junru Shao <junrushao1994@gmail.com> Co-authored-by: Xiyou Zhou <xiyou@octoml.ai> * WIP * address comments and changed tensorized comparator * update * nit * fix example * lint * lint * lint * remove unused * trigger ci * clang-format * fix * rebase Co-authored-by: Siyuan Feng <Hzfengsy@sjtu.edu.cn> Co-authored-by: Bohan Hou <32121147+spectrometerHBH@users.noreply.github.com> Co-authored-by: Hongyi Jin <3231950289@qq.com> Co-authored-by: Ruihang Lai <lairuihangdongdong@qq.com> Co-authored-by: Junru Shao <junrushao1994@gmail.com> Co-authored-by: Xiyou Zhou <xiyou@octoml.ai>
Configuration menu - View commit details
-
Copy full SHA for 5e7438f - Browse repository at this point
Copy the full SHA 5e7438fView commit details -
[microTVM][tutorial] Add ENV variable to enable testing on physical h…
Configuration menu - View commit details
-
Copy full SHA for 884fee4 - Browse repository at this point
Copy the full SHA 884fee4View commit details -
[microNPU] Refactor base address determination to codegen (#9929)
This commit introduces BaseAddress ObjectRef to determine base addresses in the codegen for microNPU. This is required when multiple memory pools become available. Thus, base addresses could not be statically determined in the source module.
Configuration menu - View commit details
-
Copy full SHA for b972877 - Browse repository at this point
Copy the full SHA b972877View commit details -
Add FP requantize flow. Set float32 flow by default for llvm x86 targ…
…ets with (#9637) sse4.1 support
Configuration menu - View commit details
-
Copy full SHA for ffff8dd - Browse repository at this point
Copy the full SHA ffff8ddView commit details -
[Relay][DefuseOps pass] bug fix: To support function body types other…
… than call node (#10069) Co-authored-by: pranav jonnalagadda-SJ1 Eng_ML <pjonnalagadd@sj1mach1.caveonetworks.com>
Configuration menu - View commit details
-
Copy full SHA for abdccf9 - Browse repository at this point
Copy the full SHA abdccf9View commit details -
[Fix Bug]fix the bug of tensorflow frontend when parsing Range layer …
…(#9999) Co-authored-by: wangjiuyang <wang.jiuyang@intellif.com>
Configuration menu - View commit details
-
Copy full SHA for 92cd754 - Browse repository at this point
Copy the full SHA 92cd754View commit details -
[MetaSchedule][M4a] Schedule Rule: Multi-Level-Tiling (#10043)
* multi level tiling * remove tensor core related code * pylint * fix Co-authored-by: Junru Shao <junrushao1994@gmail.com>
Configuration menu - View commit details
-
Copy full SHA for ffbe491 - Browse repository at this point
Copy the full SHA ffbe491View commit details -
Revert "[Frontend] Add Span filling for frontends to Relay (#9723)" (…
…#10072) Because of the failure of LSTM conversion from Pytorch
Configuration menu - View commit details
-
Copy full SHA for 095b639 - Browse repository at this point
Copy the full SHA 095b639View commit details -
Improve the tensorflow frontend _test_spop_resource_variables to supp…
…ort tensoflow 2.6 (#9978) On tensorflow 2.4 the test is expected to fail as the generated graph is not forzen. On tensorflow 2.6 the generated graph is identified as frozen, therefore the test is not needed
Configuration menu - View commit details
-
Copy full SHA for cc8a7a2 - Browse repository at this point
Copy the full SHA cc8a7a2View commit details -
[MetaSchedule] postproc: rewrite_parallel_vectorize_unroll (#10071)
Co-authored-by: Junru Shao <junrushao1994@gmail.com> Co-authored-by: Xiyou Zhou <xiyou@octoml.ai> Co-authored-by: Bohan Hou <32121147+spectrometerHBH@users.noreply.github.com> Co-authored-by: Ruihang Lai <lairuihangdongdong@qq.com> Co-authored-by: Hongyi Jin <3231950289@qq.com> Co-authored-by: Wuwei Lin <wuwei@apache.org> Co-authored-by: Junru Shao <junrushao1994@gmail.com> Co-authored-by: Xiyou Zhou <xiyou@octoml.ai> Co-authored-by: Bohan Hou <32121147+spectrometerHBH@users.noreply.github.com> Co-authored-by: Ruihang Lai <lairuihangdongdong@qq.com> Co-authored-by: Hongyi Jin <3231950289@qq.com> Co-authored-by: Wuwei Lin <wuwei@apache.org>
Configuration menu - View commit details
-
Copy full SHA for 1935341 - Browse repository at this point
Copy the full SHA 1935341View commit details -
Clear warnings when building with MSVC. (#10059)
* Fix warning "unsafe mix of type 'const int64_t' and type 'bool' in operation" occurring in tvm::tir::HasAnn * Suppress warning "destructor never returns, potential memory leak" occurring in tvm::runtime::detail::LogFatal::~LogFatal
Configuration menu - View commit details
-
Copy full SHA for d29c801 - Browse repository at this point
Copy the full SHA d29c801View commit details -
[Makefile] Fixed error in "make clean" (#10048)
The top-level makefile should delegate `make clean` to the cmake folder of each enabled build, similar to the existing delegation of `make all` and `make runtime`.
Configuration menu - View commit details
-
Copy full SHA for 622a03c - Browse repository at this point
Copy the full SHA 622a03cView commit details -
[Relay] QLinearMatMul allows 1D weight_scale, weight_zero_point input…
…s (#10047) * fix after cr * fix after cr 2 * emptycommit * emptycommit 2nd try
Configuration menu - View commit details
-
Copy full SHA for 90e454a - Browse repository at this point
Copy the full SHA 90e454aView commit details -
Don't explicitly link libgcc.a into libtvm_runtime.so on Android (#10…
…052) Setting Android toolchain via CMAKE_TOOLCHAIN_FILE also causes necessary flags to be added. Also, newer versions of the Android NDK no longer ship libgcc.a, so this takes care of that as well.
Krzysztof Parzyszek authoredJan 26, 2022 Configuration menu - View commit details
-
Copy full SHA for 09daa88 - Browse repository at this point
Copy the full SHA 09daa88View commit details -
Change function constructors to WithFields (#9690)
* Change function constructors to WithFields Get rid of std::moves, they were causing problems * Fix bad rebase * flaky * try to trigger ci * try again
Configuration menu - View commit details
-
Copy full SHA for 248ad45 - Browse repository at this point
Copy the full SHA 248ad45View commit details
Commits on Jan 27, 2022
-
Document missing qnn operators (#10077)
The following qnn operators were missing from the relay documentation.
Ramana Radhakrishnan authoredJan 27, 2022 Configuration menu - View commit details
-
Copy full SHA for a40de47 - Browse repository at this point
Copy the full SHA a40de47View commit details -
Add temp git dir to test_cc_reviewers test case (#10058)
This decouples the test_cc_reviewers test case from the user's git configuration. The implementation reuses the TempGit structure from test_skip_ci to always use a fresh git environment.
Configuration menu - View commit details
-
Copy full SHA for e42b9a3 - Browse repository at this point
Copy the full SHA e42b9a3View commit details -
[CI] Fix Rust permissions for wasmtime and sccache (#10015)
Previously this was ran as part of `ubuntu_install_rust.sh`, as we now have multiple scripts which write as the container build user we have to fix up each time to ensure future users don't break.
Configuration menu - View commit details
-
Copy full SHA for f161bc2 - Browse repository at this point
Copy the full SHA f161bc2View commit details -
Configuration menu - View commit details
-
Copy full SHA for 4b0558c - Browse repository at this point
Copy the full SHA 4b0558cView commit details -
Configuration menu - View commit details
-
Copy full SHA for f93f2a6 - Browse repository at this point
Copy the full SHA f93f2a6View commit details -
[CI][Fix] Remove additional qnn.op.transpose_conv2d from docs (#10083)
Fixes CI after #10077, and replaces misuse elsewhere. Change-Id: I095fc8ea2b8d268b09538832cba1f5482a73a9d9
Configuration menu - View commit details
-
Copy full SHA for fa317ed - Browse repository at this point
Copy the full SHA fa317edView commit details
Commits on Jan 28, 2022
-
Configuration menu - View commit details
-
Copy full SHA for e6af874 - Browse repository at this point
Copy the full SHA e6af874View commit details -
[microNPU] Removing constant args from PrimFunc (#9951)
Before this commit, microNPU creates PrimFunc as if it accepts constants from the callee. This commit changes the PrimFunc to remove the constants as an argument to PrimFunc as they are not provided from the main function.
Configuration menu - View commit details
-
Copy full SHA for 7b9fd1e - Browse repository at this point
Copy the full SHA 7b9fd1eView commit details -
[Relay] fix incorrect binding of Lets in ANF conversion (#10078)
* fix incorrect binding of lets in ANF conversion * add test case * remove really weird auto-import from debugging * address comments
Configuration menu - View commit details
-
Copy full SHA for 82d4d0f - Browse repository at this point
Copy the full SHA 82d4d0fView commit details -
[microTVM] Update Zephyr to 2.7 (#10094)
This supports the reference system added in #9853
Configuration menu - View commit details
-
Copy full SHA for 3af9c30 - Browse repository at this point
Copy the full SHA 3af9c30View commit details -
[Runtime][PipelineExecutor] Pipeline Executor Sequential execution (#…
…10082) * [Runtime][PipelineExecutor] Pipeline Executor Sequential execution In the first, adding the "get output" logic. Secondly, adding the the sequential executing logic of pipeline executor. In the last, testing the pipeline executor interface and checking the output data. * Address review comments. Co-authored-by: Cody Yu <comaniac0422@gmail.com> * trigger build. Co-authored-by: Cody Yu <comaniac0422@gmail.com>
Configuration menu - View commit details
-
Copy full SHA for 80d4d05 - Browse repository at this point
Copy the full SHA 80d4d05View commit details -
Configuration menu - View commit details
-
Copy full SHA for 85d42f8 - Browse repository at this point
Copy the full SHA 85d42f8View commit details -
[Hexagon] Update hexagon API build instruction and cleanup hexagon_pr…
…oxy_rpc (#10068) * Fix hexagon api build and Update Readme * Cleanup hexagon_proxy_rpc * Target Hack * Remove hack * address @cconvey comments * remove the rest of proxy rpc
Configuration menu - View commit details
-
Copy full SHA for 6a274af - Browse repository at this point
Copy the full SHA 6a274afView commit details
Commits on Jan 29, 2022
-
[MetaSchedule][M4a] Mutator: Mutate-Tile-Size (#10092)
* [MetaSchedule][M4a] Mutator: Mutate-Tile-Size Co-authored-by: Junru Shao <junrushao1994@gmail.com> Co-authored-by: Xiyou Zhou <xiyou@octoml.ai> Co-authored-by: Bohan Hou <32121147+spectrometerHBH@users.noreply.github.com> Co-authored-by: Siyuan Feng <Hzfengsy@sjtu.edu.cn> Co-authored-by: Hongyi Jin <3231950289@qq.com> Co-authored-by: Wuwei Lin <wuwei@apache.org> * Python 3.8 has no `math.prod` Co-authored-by: Junru Shao <junrushao1994@gmail.com> Co-authored-by: Xiyou Zhou <xiyou@octoml.ai> Co-authored-by: Bohan Hou <32121147+spectrometerHBH@users.noreply.github.com> Co-authored-by: Siyuan Feng <Hzfengsy@sjtu.edu.cn> Co-authored-by: Hongyi Jin <3231950289@qq.com> Co-authored-by: Wuwei Lin <wuwei@apache.org>
Configuration menu - View commit details
-
Copy full SHA for 4d0dac3 - Browse repository at this point
Copy the full SHA 4d0dac3View commit details -
[TE] Fix Const Int bound analysis to handle uints for division (#10102)
* case to handle uints * add unit test
Configuration menu - View commit details
-
Copy full SHA for 21154c2 - Browse repository at this point
Copy the full SHA 21154c2View commit details -
[Op][Topi] Gather, GatherND, Take can accept unsigned integers as ind…
…ices (#10080) * take rel * gather and more tests * gathernd case * lint * remove test which invalidates take preconditions * re-add test * fix dumb test failure oopsie
Configuration menu - View commit details
-
Copy full SHA for 0fb5ae2 - Browse repository at this point
Copy the full SHA 0fb5ae2View commit details -
[MetaSchedule][M4b] Testcases for TensorRT builder/runner (#10055)
Co-authored-by: Siyuan Feng <Hzfengsy@sjtu.edu.cn> Co-authored-by: Bohan Hou <32121147+spectrometerHBH@users.noreply.github.com> Co-authored-by: Hongyi Jin <3231950289@qq.com> Co-authored-by: Ruihang Lai <lairuihangdongdong@qq.com> Co-authored-by: Junru Shao <junrushao1994@gmail.com> Co-authored-by: Xiyou Zhou <xiyou@octoml.ai>
Configuration menu - View commit details
-
Copy full SHA for ba65197 - Browse repository at this point
Copy the full SHA ba65197View commit details -
[MetaSchedule] postproc: rewrite_cooperative_fetch (#10081)
Co-authored-by: Junru Shao <junrushao1994@gmail.com> Co-authored-by: Xiyou Zhou <xiyou@octoml.ai> Co-authored-by: Bohan Hou <32121147+spectrometerHBH@users.noreply.github.com> Co-authored-by: Ruihang Lai <lairuihangdongdong@qq.com> Co-authored-by: Hongyi Jin <3231950289@qq.com> Co-authored-by: Wuwei Lin <wuwei@apache.org> Co-authored-by: Junru Shao <junrushao1994@gmail.com> Co-authored-by: Xiyou Zhou <xiyou@octoml.ai> Co-authored-by: Bohan Hou <32121147+spectrometerHBH@users.noreply.github.com> Co-authored-by: Ruihang Lai <lairuihangdongdong@qq.com> Co-authored-by: Hongyi Jin <3231950289@qq.com> Co-authored-by: Wuwei Lin <wuwei@apache.org>
Configuration menu - View commit details
-
Copy full SHA for 538347e - Browse repository at this point
Copy the full SHA 538347eView commit details
Commits on Jan 30, 2022
-
[Op][Topi] 5 ops can accept unsigned integers as indices (#10098)
* tests passed * reformat * add uint test for unravel_index
Configuration menu - View commit details
-
Copy full SHA for 1f9c76b - Browse repository at this point
Copy the full SHA 1f9c76bView commit details -
[MetaSchedule][M4a] User-API: Tune-TE/TIR/Relay (#10079)
* Add tuning scripts for tir, te & relay. Co-authored-by: Junru Shao <junrushao1994@gmail.com> Co-authored-by: Bohan Hou <32121147+spectrometerHBH@users.noreply.github.com> Co-authored-by: Ruihang Lai <lairuihangdongdong@qq.com> Co-authored-by: Hongyi Jin <3231950289@qq.com> Co-authored-by: Wuwei Lin <wuwei@apache.org> Co-authored-by: Siyuan Feng <Hzfengsy@sjtu.edu.cn> Minor fix. Nits. Add back tests. * slightly improve tune.py Co-authored-by: Junru Shao <junrushao1994@gmail.com>
Configuration menu - View commit details
-
Copy full SHA for 779dc51 - Browse repository at this point
Copy the full SHA 779dc51View commit details
Commits on Jan 31, 2022
-
Configuration menu - View commit details
-
Copy full SHA for 5029c9d - Browse repository at this point
Copy the full SHA 5029c9dView commit details -
[Fix Bug]fix the bugs of keras frontend when parsing LSTM, GRU, RNN …
…layers. (#9850) * [Fix Bug]fix the bugs of keras frontend when parsing LSTM, GRU, RNN layers. * Reformat files with black formatter. Co-authored-by: AndrewZhaoLuo <andrew.zhao.luo@gmail.com>
Configuration menu - View commit details
-
Copy full SHA for d8d0053 - Browse repository at this point
Copy the full SHA d8d0053View commit details -
[Caffe Frontend] Add support for Power layer (#9655)
Co-authored-by: tangkun <kun.tang@hexintek.com>
Configuration menu - View commit details
-
Copy full SHA for f2d60fe - Browse repository at this point
Copy the full SHA f2d60feView commit details -
Use ci.py explicitly in docs building instructions (#9971)
This adds `ci.py` to the docs to make it more clear how to easily build the docs locally. This also re-arranges CI following the merging of all CI steps to run concurrently since there's no need to run the Sphinx precheck during GPU unit tests. This still preserves it though in the docs step as a way to quickly bail out if there are formatting errors so the full tutorials don't get built. Co-authored-by: driazati <driazati@users.noreply.github.com>
Configuration menu - View commit details
-
Copy full SHA for b365586 - Browse repository at this point
Copy the full SHA b365586View commit details -
[microTVM] Include standalone_crt dependencies in MLF (#10095)
* Adds runtime to AOTExecutorFactoryModule * Standalone CRT files are added to MLF tarball if runtime is crt * external_dependencies info added to metadata.json for crt runtime * microNPU demo Makefile references standalone crt files from MLF tarball
Configuration menu - View commit details
-
Copy full SHA for 3b20c21 - Browse repository at this point
Copy the full SHA 3b20c21View commit details -
[ETHOSN] Per-tensor support for int8 operations (#10018)
* Per-axis quantization to follow
Configuration menu - View commit details
-
Copy full SHA for 3de25b8 - Browse repository at this point
Copy the full SHA 3de25b8View commit details -
[CI] Update DGL in gpu image (#10111)
* validating ci_gpu:20220128-070420-fa317edf7 * remove gcn tutorial workaround * update ci-gpu image to v0.81
Configuration menu - View commit details
-
Copy full SHA for 1d01e28 - Browse repository at this point
Copy the full SHA 1d01e28View commit details -
[microNPU] Add support for nearest neighbor and bilinear upsampling (…
…#9841) * [microNPU] Add support for nearest neighbor and bilinear upsampling Adds support for 2x2 nearest neighbor and bilinear upsampling. In the case of bilinear upsampling with align_corners set to true, the upsampling size must be `2*input_size - 1` (as opposed to `2*input_size`). Change-Id: I95d215eabfaac983629dcdedcda2b90efb8e0ddf * rebase and add support for no-upsampling case. Change-Id: I840d8ee3671a40c5c99f22119442c349dbed39cf
Configuration menu - View commit details
-
Copy full SHA for 02a7a41 - Browse repository at this point
Copy the full SHA 02a7a41View commit details -
[Bugfix][Op] Fix shape inference of adv_index (#9717)
* init * test * lint
Configuration menu - View commit details
-
Copy full SHA for dad8f62 - Browse repository at this point
Copy the full SHA dad8f62View commit details -
Configuration menu - View commit details
-
Copy full SHA for 62e161f - Browse repository at this point
Copy the full SHA 62e161fView commit details -
Configuration menu - View commit details
-
Copy full SHA for 6b4abb9 - Browse repository at this point
Copy the full SHA 6b4abb9View commit details -
Configuration menu - View commit details
-
Copy full SHA for b6e357b - Browse repository at this point
Copy the full SHA b6e357bView commit details -
Configuration menu - View commit details
-
Copy full SHA for f25d3fc - Browse repository at this point
Copy the full SHA f25d3fcView commit details -
Configuration menu - View commit details
-
Copy full SHA for 829634b - Browse repository at this point
Copy the full SHA 829634bView commit details -
Add in an example of the dumping mode and some description of the cha…
…nges in the readme
Configuration menu - View commit details
-
Copy full SHA for acf14a9 - Browse repository at this point
Copy the full SHA acf14a9View commit details -
Configuration menu - View commit details
-
Copy full SHA for 751df45 - Browse repository at this point
Copy the full SHA 751df45View commit details -
Configuration menu - View commit details
-
Copy full SHA for c517626 - Browse repository at this point
Copy the full SHA c517626View commit details -
Configuration menu - View commit details
-
Copy full SHA for aab7be4 - Browse repository at this point
Copy the full SHA aab7be4View commit details -
Configuration menu - View commit details
-
Copy full SHA for a693b9f - Browse repository at this point
Copy the full SHA a693b9fView commit details -
Configuration menu - View commit details
-
Copy full SHA for 1616d2a - Browse repository at this point
Copy the full SHA 1616d2aView commit details -
Configuration menu - View commit details
-
Copy full SHA for 79c9238 - Browse repository at this point
Copy the full SHA 79c9238View commit details -
Configuration menu - View commit details
-
Copy full SHA for 5a2b5b0 - Browse repository at this point
Copy the full SHA 5a2b5b0View commit details -
Configuration menu - View commit details
-
Copy full SHA for 74a3605 - Browse repository at this point
Copy the full SHA 74a3605View commit details -
[FIX] BYOC compilation error due to missing files (#1)
* [ add ] vat_matmul runtime files * [ update ] get rid of pushing 0s to ACC * add comment about the change in codegen.cc * restore ACC buffer initialization * [ add ] compute missing fields of VTA config
Configuration menu - View commit details
-
Copy full SHA for e5a97a2 - Browse repository at this point
Copy the full SHA e5a97a2View commit details -
Configuration menu - View commit details
-
Copy full SHA for c8e7170 - Browse repository at this point
Copy the full SHA c8e7170View commit details -
Configuration menu - View commit details
-
Copy full SHA for 23499c4 - Browse repository at this point
Copy the full SHA 23499c4View commit details -
Configuration menu - View commit details
-
Copy full SHA for 393717a - Browse repository at this point
Copy the full SHA 393717aView commit details -
Configuration menu - View commit details
-
Copy full SHA for 07d1b13 - Browse repository at this point
Copy the full SHA 07d1b13View commit details -
Configuration menu - View commit details
-
Copy full SHA for 2fbdc3f - Browse repository at this point
Copy the full SHA 2fbdc3fView commit details -
Configuration menu - View commit details
-
Copy full SHA for 4988b6b - Browse repository at this point
Copy the full SHA 4988b6bView commit details -
Configuration menu - View commit details
-
Copy full SHA for b91106b - Browse repository at this point
Copy the full SHA b91106bView commit details -
Configuration menu - View commit details
-
Copy full SHA for b5c5113 - Browse repository at this point
Copy the full SHA b5c5113View commit details -
Configuration menu - View commit details
-
Copy full SHA for beb7ef9 - Browse repository at this point
Copy the full SHA beb7ef9View commit details -
Configuration menu - View commit details
-
Copy full SHA for 3ffed80 - Browse repository at this point
Copy the full SHA 3ffed80View commit details -
Configuration menu - View commit details
-
Copy full SHA for e664064 - Browse repository at this point
Copy the full SHA e664064View commit details -
Configuration menu - View commit details
-
Copy full SHA for eb07d99 - Browse repository at this point
Copy the full SHA eb07d99View commit details -
Configuration menu - View commit details
-
Copy full SHA for 0bc1ca2 - Browse repository at this point
Copy the full SHA 0bc1ca2View commit details -
Configuration menu - View commit details
-
Copy full SHA for 74ae7e1 - Browse repository at this point
Copy the full SHA 74ae7e1View commit details -
Configuration menu - View commit details
-
Copy full SHA for 2d13366 - Browse repository at this point
Copy the full SHA 2d13366View commit details -
Configuration menu - View commit details
-
Copy full SHA for 1e2e4f1 - Browse repository at this point
Copy the full SHA 1e2e4f1View commit details -
Configuration menu - View commit details
-
Copy full SHA for 1485122 - Browse repository at this point
Copy the full SHA 1485122View commit details -
Configuration menu - View commit details
-
Copy full SHA for 156cdf4 - Browse repository at this point
Copy the full SHA 156cdf4View commit details -
Configuration menu - View commit details
-
Copy full SHA for f8d8cbd - Browse repository at this point
Copy the full SHA f8d8cbdView commit details -
Configuration menu - View commit details
-
Copy full SHA for 6ccaa55 - Browse repository at this point
Copy the full SHA 6ccaa55View commit details -
Configuration menu - View commit details
-
Copy full SHA for c722868 - Browse repository at this point
Copy the full SHA c722868View commit details -
Configuration menu - View commit details
-
Copy full SHA for 0de8947 - Browse repository at this point
Copy the full SHA 0de8947View commit details -
Configuration menu - View commit details
-
Copy full SHA for d74598f - Browse repository at this point
Copy the full SHA d74598fView commit details -
Configuration menu - View commit details
-
Copy full SHA for fc67b74 - Browse repository at this point
Copy the full SHA fc67b74View commit details -
Configuration menu - View commit details
-
Copy full SHA for 67903a1 - Browse repository at this point
Copy the full SHA 67903a1View commit details -
Configuration menu - View commit details
-
Copy full SHA for 180e8a9 - Browse repository at this point
Copy the full SHA 180e8a9View commit details -
Configuration menu - View commit details
-
Copy full SHA for 9a3300c - Browse repository at this point
Copy the full SHA 9a3300cView commit details -
Configuration menu - View commit details
-
Copy full SHA for 71f7eb0 - Browse repository at this point
Copy the full SHA 71f7eb0View commit details -
Configuration menu - View commit details
-
Copy full SHA for 2267c03 - Browse repository at this point
Copy the full SHA 2267c03View commit details -
Configuration menu - View commit details
-
Copy full SHA for 3f838dc - Browse repository at this point
Copy the full SHA 3f838dcView commit details -
Configuration menu - View commit details
-
Copy full SHA for 9fd41db - Browse repository at this point
Copy the full SHA 9fd41dbView commit details -
Configuration menu - View commit details
-
Copy full SHA for 94eec1a - Browse repository at this point
Copy the full SHA 94eec1aView commit details -
Configuration menu - View commit details
-
Copy full SHA for 6155d28 - Browse repository at this point
Copy the full SHA 6155d28View commit details -
Configuration menu - View commit details
-
Copy full SHA for 502f09c - Browse repository at this point
Copy the full SHA 502f09cView commit details -
[REFACTOR] Compile to ILA Asm (#11)
* change to uint8_t in ila runtime * [ refactor ] pre-compile to ILA asm * [ impl ] jit * [ add ] mlp model * [ add ] quantized model in PT * [ fix ] run quantized * [ refactor ] AoT compiler * hmm? I dont remember I touched this file * [ fix ] naming issue and resolve some warnings * [ fix ] turn off size check * [ refactor ] cast according to annotation * [ fix ] dtype
Configuration menu - View commit details
-
Copy full SHA for 80774b4 - Browse repository at this point
Copy the full SHA 80774b4View commit details -
Configuration menu - View commit details
-
Copy full SHA for 1573922 - Browse repository at this point
Copy the full SHA 1573922View commit details -
Configuration menu - View commit details
-
Copy full SHA for 15b8d2a - Browse repository at this point
Copy the full SHA 15b8d2aView commit details -
Configuration menu - View commit details
-
Copy full SHA for 39cbab4 - Browse repository at this point
Copy the full SHA 39cbab4View commit details -
Configuration menu - View commit details
-
Copy full SHA for 4074b14 - Browse repository at this point
Copy the full SHA 4074b14View commit details -
Configuration menu - View commit details
-
Copy full SHA for d7b5d11 - Browse repository at this point
Copy the full SHA d7b5d11View commit details -
Configuration menu - View commit details
-
Copy full SHA for a64fdfd - Browse repository at this point
Copy the full SHA a64fdfdView commit details -
Configuration menu - View commit details
-
Copy full SHA for 2375d32 - Browse repository at this point
Copy the full SHA 2375d32View commit details -
flexnlp lstm backend driver is completed, end-to-end testflow passed (#3
Configuration menu - View commit details
-
Copy full SHA for 67ae67c - Browse repository at this point
Copy the full SHA 67ae67cView commit details -
Configuration menu - View commit details
-
Copy full SHA for ddb4582 - Browse repository at this point
Copy the full SHA ddb4582View commit details -
Configuration menu - View commit details
-
Copy full SHA for caf8765 - Browse repository at this point
Copy the full SHA caf8765View commit details -
Configuration menu - View commit details
-
Copy full SHA for 70d130d - Browse repository at this point
Copy the full SHA 70d130dView commit details -
Op name passed to python driver (#8)
* end-to-end codegen for ILA-VTA * [ add ] tests * ignore instr_log * tweak PR * get rid of warnings * remove logging in pattern matching * [ add ] instruction for running the end-to-end test script * [ init ] bias add codegen * add data loading * [ add ] bias add test case * [ fix ] datatype conversion * change to int8 inputs * integrate 3la driver into tvm framework * lstm flexnlp backend driver added * [ init ] relu runtime * [ add ] relu runtime code * Add exact matcher * fix data loading * [ update ] tests * [ refactor ] code * [ add ] comments * remove redundant submodule in the python test folder; redirect python driver path inside TVM in the ilaflex_runtime * Simplify implementation, correct pattern bugs, and add more tests * flexnlp lstm end-to-end flow complete * Correct inaccurate comment * Reformat comment * Throw in refs because why not * Need to visit matched args to find all matches * Move utility checkers to exact_matcher file (they will come in handy again) * Add test scaling the pattern matching to the speech-to-text model * Unused function * Add test case of not matching free var in match block * Incorrect dimension * set ila driver as external python scripts located through /home/leeoh/3la/pattern_matching/3la_ILA_tensor_op/ path * 3la flexnlp python driver as standalone path; small fixed in include module in flex_linear.py * Correct attribute names and also include primitive * pass op_name when offloading calculation Co-authored-by: AD1024 <dh63@cs.washington.edu> Co-authored-by: Steven S. Lyubomirsky <sslyu@cs.washington.edu> Co-authored-by: Bo-Yuan Huang <Bo-Yuan-Huang@users.noreply.github.com>
Configuration menu - View commit details
-
Copy full SHA for 99cff9b - Browse repository at this point
Copy the full SHA 99cff9bView commit details -
Configuration menu - View commit details
-
Copy full SHA for aa5feac - Browse repository at this point
Copy the full SHA aa5feacView commit details -
Configuration menu - View commit details
-
Copy full SHA for 8897d39 - Browse repository at this point
Copy the full SHA 8897d39View commit details -
Configuration menu - View commit details
-
Copy full SHA for bbd8a4f - Browse repository at this point
Copy the full SHA bbd8a4fView commit details -
Configuration menu - View commit details
-
Copy full SHA for 40d029f - Browse repository at this point
Copy the full SHA 40d029fView commit details -
Configuration menu - View commit details
-
Copy full SHA for c2b969f - Browse repository at this point
Copy the full SHA c2b969fView commit details -
Configuration menu - View commit details
-
Copy full SHA for c03a201 - Browse repository at this point
Copy the full SHA c03a201View commit details -
Configuration menu - View commit details
-
Copy full SHA for d650ea8 - Browse repository at this point
Copy the full SHA d650ea8View commit details -
Configuration menu - View commit details
-
Copy full SHA for b682022 - Browse repository at this point
Copy the full SHA b682022View commit details -
Configuration menu - View commit details
-
Copy full SHA for 0527549 - Browse repository at this point
Copy the full SHA 0527549View commit details -
Configuration menu - View commit details
-
Copy full SHA for aba60cd - Browse repository at this point
Copy the full SHA aba60cdView commit details -
Configuration menu - View commit details
-
Copy full SHA for e3dadec - Browse repository at this point
Copy the full SHA e3dadecView commit details -
Configuration menu - View commit details
-
Copy full SHA for 8bd8387 - Browse repository at this point
Copy the full SHA 8bd8387View commit details -
Configuration menu - View commit details
-
Copy full SHA for f1ec7de - Browse repository at this point
Copy the full SHA f1ec7deView commit details -
Configuration menu - View commit details
-
Copy full SHA for 0d5151f - Browse repository at this point
Copy the full SHA 0d5151fView commit details -
Configuration menu - View commit details
-
Copy full SHA for 88eba3b - Browse repository at this point
Copy the full SHA 88eba3bView commit details -
Configuration menu - View commit details
-
Copy full SHA for 04d23b7 - Browse repository at this point
Copy the full SHA 04d23b7View commit details -
Configuration menu - View commit details
-
Copy full SHA for c0c6cb3 - Browse repository at this point
Copy the full SHA c0c6cb3View commit details -
Configuration menu - View commit details
-
Copy full SHA for 3da68f3 - Browse repository at this point
Copy the full SHA 3da68f3View commit details -
Configuration menu - View commit details
-
Copy full SHA for 8fa62a7 - Browse repository at this point
Copy the full SHA 8fa62a7View commit details -
Configuration menu - View commit details
-
Copy full SHA for 06a5e4a - Browse repository at this point
Copy the full SHA 06a5e4aView commit details -
Configuration menu - View commit details
-
Copy full SHA for 3f0092c - Browse repository at this point
Copy the full SHA 3f0092cView commit details -
Configuration menu - View commit details
-
Copy full SHA for 1287c63 - Browse repository at this point
Copy the full SHA 1287c63View commit details -
Configuration menu - View commit details
-
Copy full SHA for 5a2610b - Browse repository at this point
Copy the full SHA 5a2610bView commit details -
Configuration menu - View commit details
-
Copy full SHA for b421a01 - Browse repository at this point
Copy the full SHA b421a01View commit details -
Configuration menu - View commit details
-
Copy full SHA for 7abff9e - Browse repository at this point
Copy the full SHA 7abff9eView commit details -
Configuration menu - View commit details
-
Copy full SHA for c9dbc53 - Browse repository at this point
Copy the full SHA c9dbc53View commit details -
Configuration menu - View commit details
-
Copy full SHA for d202cfa - Browse repository at this point
Copy the full SHA d202cfaView commit details -
Use a callback in the exact matcher (#18)
* Don't use checked_type for annotating types in the matcher (breaks tests and relies on type checking) * Add callback feature to exact matcher, expand tests, simplify recent additions
Configuration menu - View commit details
-
Copy full SHA for 733eafb - Browse repository at this point
Copy the full SHA 733eafbView commit details -
Configuration menu - View commit details
-
Copy full SHA for ce73b9c - Browse repository at this point
Copy the full SHA ce73b9cView commit details -
Configuration menu - View commit details
-
Copy full SHA for eb93b16 - Browse repository at this point
Copy the full SHA eb93b16View commit details -
Configuration menu - View commit details
-
Copy full SHA for 6de2c30 - Browse repository at this point
Copy the full SHA 6de2c30View commit details -
Configuration menu - View commit details
-
Copy full SHA for 9a7184c - Browse repository at this point
Copy the full SHA 9a7184cView commit details -
Configuration menu - View commit details
-
Copy full SHA for 4658a43 - Browse repository at this point
Copy the full SHA 4658a43View commit details -
Configuration menu - View commit details
-
Copy full SHA for 82e77ff - Browse repository at this point
Copy the full SHA 82e77ffView commit details -
Configuration menu - View commit details
-
Copy full SHA for 7a56788 - Browse repository at this point
Copy the full SHA 7a56788View commit details -
Configuration menu - View commit details
-
Copy full SHA for fe77da1 - Browse repository at this point
Copy the full SHA fe77da1View commit details -
Configuration menu - View commit details
-
Copy full SHA for 76b3deb - Browse repository at this point
Copy the full SHA 76b3debView commit details -
Configuration menu - View commit details
-
Copy full SHA for d947453 - Browse repository at this point
Copy the full SHA d947453View commit details -
Configuration menu - View commit details
-
Copy full SHA for 3fe4e0a - Browse repository at this point
Copy the full SHA 3fe4e0aView commit details -
Configuration menu - View commit details
-
Copy full SHA for 51e8f58 - Browse repository at this point
Copy the full SHA 51e8f58View commit details -
Configuration menu - View commit details
-
Copy full SHA for c61affc - Browse repository at this point
Copy the full SHA c61affcView commit details -
Configuration menu - View commit details
-
Copy full SHA for 8270655 - Browse repository at this point
Copy the full SHA 8270655View commit details -
Configuration menu - View commit details
-
Copy full SHA for cd13d9c - Browse repository at this point
Copy the full SHA cd13d9cView commit details -
Configuration menu - View commit details
-
Copy full SHA for 7e131f8 - Browse repository at this point
Copy the full SHA 7e131f8View commit details -
Configuration menu - View commit details
-
Copy full SHA for ce097b4 - Browse repository at this point
Copy the full SHA ce097b4View commit details -
Configuration menu - View commit details
-
Copy full SHA for 9ef9519 - Browse repository at this point
Copy the full SHA 9ef9519View commit details -
Configuration menu - View commit details
-
Copy full SHA for b366b79 - Browse repository at this point
Copy the full SHA b366b79View commit details -
Configuration menu - View commit details
-
Copy full SHA for beabf4b - Browse repository at this point
Copy the full SHA beabf4bView commit details -
Configuration menu - View commit details
-
Copy full SHA for 0b5b021 - Browse repository at this point
Copy the full SHA 0b5b021View commit details -
Configuration menu - View commit details
-
Copy full SHA for 080c058 - Browse repository at this point
Copy the full SHA 080c058View commit details -
Configuration menu - View commit details
-
Copy full SHA for 187c9a7 - Browse repository at this point
Copy the full SHA 187c9a7View commit details -
Configuration menu - View commit details
-
Copy full SHA for 3541210 - Browse repository at this point
Copy the full SHA 3541210View commit details -
Configuration menu - View commit details
-
Copy full SHA for 0eb349b - Browse repository at this point
Copy the full SHA 0eb349bView commit details -
Configuration menu - View commit details
-
Copy full SHA for fce3048 - Browse repository at this point
Copy the full SHA fce3048View commit details -
Configuration menu - View commit details
-
Copy full SHA for 0c09d2a - Browse repository at this point
Copy the full SHA 0c09d2aView commit details -
Configuration menu - View commit details
-
Copy full SHA for d5b63fb - Browse repository at this point
Copy the full SHA d5b63fbView commit details -
Configuration menu - View commit details
-
Copy full SHA for 1973194 - Browse repository at this point
Copy the full SHA 1973194View commit details -
Configuration menu - View commit details
-
Copy full SHA for 7647138 - Browse repository at this point
Copy the full SHA 7647138View commit details -
Configuration menu - View commit details
-
Copy full SHA for f0365ee - Browse repository at this point
Copy the full SHA f0365eeView commit details -
Configuration menu - View commit details
-
Copy full SHA for debce2d - Browse repository at this point
Copy the full SHA debce2dView commit details -
Configuration menu - View commit details
-
Copy full SHA for 82699db - Browse repository at this point
Copy the full SHA 82699dbView commit details