mirror of
https://github.com/nomic-ai/kompute.git
synced 2026-05-11 00:49:58 +00:00
13 KiB
13 KiB
Changelog
v0.6.0
Implemented enhancements:
- Add simple test for Python
log\_levelfunction #120 - Add further numpy support #104
- SWIG syntax error - change order of keywords. #94
- Create mocks to isolate unit tests for components #8
- Disallowing zero sized tensors #129 (alexander-g)
- Added further tests to CI and provide Dockerimage with builds to swiftshader #119 (axsaucedo)
- Workgroups for Python #116 (alexander-g)
- Ubuntu CI #115 (alexander-g)
- Faster set_data() #109 (alexander-g)
- String parameter for eval_algo_str methods in Python #105 (alexander-g)
- Added numpy() method #103 (alexander-g)
Fixed bugs:
- [PYTHON] Support string parameter instead of list for eval_algo_data when passing raw shader as string #93
- [PYTHON] Fix log_level on the python implementation (using pybind's logging functions) #92
Closed issues:
- Add documentation for custom operations #128
- Numpy Array Support and Work Group Configuration in Python Kompute #124
- Remove references to spdlog in python module #122
- Setup automated CI testing for PRs using GitHub actions #114
- Python example type error (pyshader). #111
- Update all references to operations to not use template #101
- Getting a undefined reference error while creating a Kompute Manager #100
Merged pull requests:
- 122 remove spdlog references in python #123 (axsaucedo)
- Native logging for Python #118 (alexander-g)
- Fixes for the c++ Simple and Extended examples in readme #108 (aliPMPAINT)
- Fix building shaders on native linux #102 (aliPMPAINT)
v0.5.1 (2020-11-12)
Implemented enhancements:
- Remove the template params from OpAlgoBase for dispatch layout #57
- Enable layout to be configured dynamically within shaders #26
- replaced "static unsigned const" to "static const unsigned" to avoid SWIG parsing error. #95 (0x0f0f0f)
- Added python bindings with kp as python module #88 (axsaucedo)
Closed issues:
Merged pull requests:
v0.5.0 (2020-11-08)
Implemented enhancements:
- Adding Python package for Kompute #87
- Python shader extension #91 (axsaucedo)
- Enhanced python build #89 (axsaucedo)
Closed issues:
v0.4.1 (2020-11-01)
Implemented enhancements:
- Upgrade build to support VulkanHPP 1.2.154 < 1.2.158 #82
- Add Android example for Kompute #23
- Fix compatibility for Vulkan HPP 1.2.155 and above #83 (axsaucedo)
- codespell spelling fixes #80 (pH5)
Closed issues:
- Android example throws runtime error. #77
- Document the utilities to convert shaders into C++ header files #53
- Document the three types of memory ownership in classes - never, optional and always #31
Merged pull requests:
- Add link to official Vulkan website to download the SDK #79 (DonaldWhyte)
- 77 Fix end to end examples by creating tensors on separate sequence #78 (axsaucedo)
v0.4.0 (2020-10-18)
Implemented enhancements:
- Error compiling on ubuntu 20.04 #67
- Add explicit multi-threading interfaces to ensure correctness when running in parallel #51
Fixed bugs:
- Ensure sequences are cleared when begin is run #74
Merged pull requests:
- 74 Fixing manager default sequence creation #75 (axsaucedo)
- Adding Asynchronous Processing Capabilities with Multiple Queue Support #73 (axsaucedo)
- Fix README typo #71 (nihui)
v0.3.2 (2020-10-04)
Implemented enhancements:
Fixed bugs:
- Fix bug in OpAlgoRhsLhs #61
Closed issues:
- Change c++ to 14 from 17 for support with older frameworks #59
Merged pull requests:
- Updated readme and single kompute for 0.3.2 #69 (axsaucedo)
- Added android example and upgraded build configurations #68 (axsaucedo)
- Added readme to explain high level explanation for Godot example #65 (axsaucedo)
- Removing vulkan dependencies in examples #64 (axsaucedo)
- Updated godot example to use logistic regression usecase #63 (axsaucedo)
v0.3.1 (2020-09-20)
Implemented enhancements:
- Add example of how vulkan kompute can be used for ML in Godot Game Engine #60
Merged pull requests:
v0.3.0 (2020-09-19)
Implemented enhancements:
- Make Kompute installable locally to work with examples #58
- Remove ability to copy output parameters from OpAlgoBase now that there's OpTensorSync #56
0.3.0 (2020-09-13)
Implemented enhancements:
- Add tests and documentation for loops passing data to/from device #50
- Add preSubmit function to OpBase to account for multiple eval commands in parallel #47
- Remove vulkan commandbuffer from Tensor #42
- Provide further granularity on handling staging tensors #40
- Create operation to copy data from local to device memory with staging #39
- Add more advanced ML implementations (starting with LR, then DL, etc) #19
Fixed bugs:
- OpCreateTensor doesn't map data into GPU with OpCreateTensor for host tensors #43
v0.2.0 (2020-09-05)
Implemented enhancements:
- Migrate to GTest #37
- Move all todos in the code into github issues #33
- Remove spdlog as a required dependency #30
- Improve access to tensor underlying data for speed and ease of access #18
- Enable for compute shaders to be provided in raw form #17
- Enable OpCreateTensor for more than 1 tensor #13
- Add specialisation data to algorithm with default tensor size #11
- Add documentation with Doxygen and Sphinx #9
Fixed bugs:
- Diagnose memory profiling to ensure there are no memory leaks on objects created [CPU] #15
Merged pull requests:
v0.1.0 (2020-08-28)
* This Changelog was automatically generated by github_changelog_generator