Release v0.2.1

This release includes improvements to the tiling and DMA code generation, new networks and operators, improved CI workflows, migration to PyTest, and support for PyPi package releases.

Note: Since the release tag references the Docker container tagged with the release tag (ghcr.io/pulp-platform/deeploy:v0.2.1), the CI will initially fail. The Deeploy Docker image must be built after the release PR is merged and the CI restarted.

List of Pull Requests

• PyPi Package Deployment + Remove Banshee Dept #154
• PyTest Migration #144
• Update submodule pulp-nn-mixed #145
• Improve Profiling #138
• FP32 ReduceMean operator improvement #137
• Support for RMSNorm (Pow and Sqrt operators) #136
• Demo TinyViT compatibility with tiled Siracusa #124
• TinyViT on non-tiled Siracusa #117
• Support Fully Asynchronous DMAs #114
• Disallow shape inference #128
• Remove memory-aware node bindings #123
• Fix missing const's layout transformation and refactor NCHWtoNHWC passes #122
• Fix aliasing #125
• Support for 1D Autoencoder #98
• Refactor Logging for Improved Debugging #115
• Add reuse-tool as an SPDX license header linter #113
• Bug fixes, API Cleanup and Reduce Compiler Warning on PULP #112
• Fix PULP GEMM batch serialization #109
• Split CI Workflows by Platform and Task, Improve Formatting and Linting Reliability #108
• Refactor tiling code generation #105
• Change order of typeMatching entries #68
• Node Mangling to avoid duplication #93
• Prepare Post v0.2.0 Release #104
• Use Docker digests instead of arch-specific tags #106
• Fix Unsqueeze Op. when using ONNX opset 13 or higher (from attribute to input) #119
• Fix bias hoisting in generic GEMM with no bias #126

Added

• The publish.yml action to build a branch and push it to PyPi. The action is automatically triggered when a tag with the "v*" format is emitted.
• I created a release of Banshee so we don't need to rebuild it over and over. The Makefile now pulls that release depending on the platform.
• I bumped the onnx-graphsurgeon version such that we don't need to use NVIDIA's PyPi index anymore.
• _export_graph assigns their export type to the tensors before export.
• pytest and pytest-xdist as dependencies of Deeploy.
• A pytest.ini for the global configuration of PyTest for the project.
• conftest.py to define CLI args for PyTest for the whole project, it also defines a set of global fixtures and markers.
• pytestRunner.py contains helper functions and fixtures for the whole project.
• test_platforms.py lists the E2E tests and sorts them into marked categories (per platform and per kernel/model).
• Each platform has a test config file where a list or a dict describes the tests.
• Support for unknown number of data dimensions in the tiler
• Parallelization support for the FP32 ReduceMean operator on PULPOpen
• Extensive testing for the ReduceMean operator
• Pass to remove ReduceMean operators that don't change data content, but only its shape
• Support for RMSNorm operation via operator decomposition.
• Added Pow (Power) and Sqrt (Square Root) operation support (Parsers, Layers, Bindings, Templates, and FP32 Kernels) for the Generic platform.
• Support for input tiling for PULP FP regular and DW conv 2D.
• CI tests for tiled Siracusa FP regular and DW conv 2D, with and without bias, for skip connections, and for the demo version of TinyViT.
• Documentation for PULP FP regular and DW conv 2D and MatMul tile constraints.
• PULP ReduceMean and Slice tile constraints.
• PULP 2D FP DW conv Im2Col template and kernel, with bias support.
• Bias support for PULP 2D FP regular conv Im2Col in template & kernel.
• PULP FP DW conv 2D parser.
• FP conv 2D (simple & DW), reshape & skip connection, and TinyViT demo tests to the non-tiled Siracusa CI pipeline.
• FP bindings and mappings for PULP slice, DW conv 2D, and reduce mean operations.
• FP PULP DW conv lowering optimization pass similar to the existent one for integer version.
• RemoveEmptyConvBiasPass to the PULP optimizer.
• Add manual type inference feature (CLI: --input-type-map/--input-offset-map) to resolve ambiguities when test inputs are not representative enough
• Added a testTypeInferenceDifferentTypes test case to validate type inference for different input types
• Added _mangleNodeNames function to avoid duplicate node mappings
• Output Docker image digests per platform (amd64, arm64) after build, which is used to construct the multi-arch Docker manifest. This preventes registry clutter caused by unnecessary per-architecture Docker tags.
• AsyncDma abstraction of DMA's
• test runner per DMA and a script that tests all the DMA's
• generic Single/DoubleBufferingTilingCodeGeneration classes
• TilingVariableReplacementUpdate class that updates the variable replacement refs
• TilingHoistingMixIn class that encapsulates all the hoisting helper functions of tiling
• sorting of input memory allocations to allow references that live in the same memory level as the memory they are referencing
• a function that tests the tiling solution for correctness which currently only tests buffer allocation for byte alignment
• IntrospectiveCodeTransformation: _indexPointer(), indexVars(), dereferenceVars(). The *Vars functions index/dereference a list of variables (useful for tiling)
• NetworkContext: unravelReference() that unravels a _ReferenceBuffer until the base buffer
• NetworkContext: is_object() - helper function that determines whether the string represents a name of a local or global object
• NetworkContext: is_buffer() - helper function that determines whether the string represents a name of a buffer
• missing checks for environment variables
• _permuteHyperRectangle helper function
• Added CI badges to the README
• Added YAML linting to CI
• Added missing license headers and C header include guards
• Extended the pre-commit hooks to remove trailing whitespace, check licenses, format and lint files
• Reshape operator support for PULP (ReshapeTemplate in bindings)
• Missing class attributes in Closure.py
• reuse_skip_wrapper.py to manually skip files
• Centralized logging with DEFAULT_LOGGER, replacing print statements
• Debug logs for type checking/parsing; __repr__ for core classes
• Buffer utilities: checkNumLevels validation and sizeInBytes method
• Per–memory-level usage tracking and worst-case reporting in NetworkContext
• Memory/I/O summaries and input/output logging in deployers
• RequantHelpers.py for Neureka's TileConstraints
• Added assertion that all the graph tensors after lowering have a shape annotated
• Added testFloatGEMMnobias
• Profiling support and optional comments in generated DMA code for better traceability
• Added new waiting-strategy logic with fine-grained PerTensorWaitingStrategy
• PULPClusterEngine now accepts a n_cores parameter to set the number of cores used
• annotateNCores method to PULPDeployer that adds an n_cores key to all PULPClusterEngine templates' operatorRepresentations
• Calculate non-kernel overhead and show total time spent during profiling

Changed

• Rename package name from PULP-Deeploy to deeploy-pulp.
• Each CI workflow has been simplified to call the pytest suite with certain markers.
• Structure of Tests subdir for improved ordering
• Structure of .gitignore file for improved ordering
• Decreased L1 maximal memory limit for CI pipeline tests where compatible thanks to the implementation of Conv2D input tiling support.
• Reduced size of reshape & skip connection test, for non-tiled Siracusa memory compatibility.
• Replaced platform-specific tags (*-amd64, *-arm64) with direct digest references in Noelware/docker-manifest-action.
• mchan HAL is now reduced to bare-bones
• refactor of the IntrospectiveCodeTransformation to work on the Mako template
• refactor of memory allocation code transformation passes
• _ReferenceBuffer accepts an optional offset argument to offset the reference
• NetworkContext: hoistReference - accepts the actual buffer as reference instead of name, accepts shape, offset, and override_type arguments, and returns the actual buffer, not its name
• _mangleNodeRep -> _mangleOpRepr - the canonical name we use is OperatorRepresentation. NodeRep and ParseDict are old iterations of the name.
• rename of permutation functions to follow this convention: permute is an action that permutes something, `permutat...

v0.2.0

Release v0.2.0 (2025-07-08) #103

This release contains major architectural changes, new platform support, enhanced simulation workflows, floating-point kernel support, training infrastructure for CCT models, memory allocation strategies, and documentation improvements.

List of Pull Requests

• Prepare v0.2.0 release #102
• Add Luka as Code Owner #101
• Fix CI, Docker Files, and Documentation Workflow #100
• Chimera Platform Integration #96
• Add Tutorial and Refactor README #97
• Reduce Mean Float Template #92
• Reshape Memory Freeing and Generic Float GEMM Fixes #91
• Prepare for Release and Separate Dependencies #90
• Fix input offsets calculation #89
• Move PULP SDK to main branch/fork #88
• Finite Lifetime for IO Tensors #51
• Improved Memory Visualization and Multi-Layer Tiling Profiling #56
• Fix Linting in CI and Reformat C Files #86
• Fix Broken CMake Flow For pulp-sdk #87
• Refactor Changelog For Release #85
• ARM Docker Container and Minor Bug Fix #84
• Added Kernel for Generic Float DW Conv2D #63
• Autoselect Self-Hosted Runners if the Action is on Upstream #81
• TEST_RECENT linking on MacOS #78
• Add RV32IMF Picolibc support for Siracusa platform #66
• Improve Documentation and VSCode Support #76
• Debug Print Topology Pass and Code Transformation #75
• Find all subdirectories of Deeploy when installing with pip install #70
• Add milestone issue template #71
• Bunch of fixes and changes #58
• Add SoftHier platform #65
• rv32imf_xpulpv2 ISA support for Siracusa platform #64
• One LLVM To Compile Them All #60
• One GVSoC to Simulate Them All #59
• Add Support for CCT Last Layer Training with Embedding Dim 8-128 #55
• Add CCT Classifier Training Support #53
• L3 Bugs: DMA Struct Datatype and Maxpool Margin Error #45
• DeepQuant Quantized Linear Support #54
• Implemented Dequant Layer for Generic and Siracusa #52
• Infinite Lifetime Buffers Considered in Tiling & Memory Allocation (+ Visualization) #44
• Implemented Quant Layer for Generic and Siracusa #49
• Increase maximal Mchan DMA transfer sizes from 64KiB to 128KiB #47
• Add MiniMalloc and Decouple Memory Allocation and Tiling #40
• Float CCT Bugs on L3 #37
• Memory Allocation Strategies and Visualization #36
• Add CODEOWNERS #42
• Add Tiling Support to All CCT Kernels and Fix CCT Operators on Siracusa Platform for L2 #35
• Add Fp gemm and Softmax for Snitch platform #31
• Add Float Kernels for CCT #29
• documentation deployment #34
• main.c Float Cast Bugs #28
• Add Float GEMM on PULP with Tiling #26
• Add Float Support & Float GEMM for Generic #25
• GVSOC support for the Snitch Cluster platform #23
• Snitch Cluster Tiling Support #22
• Snitch support integration #14
• Update bibtex citation #20
• the PR template location, bump min python to 3.10, change install command #17
• Add pre-commit for python formatting #15
• FP integration (v2) #12
• shell for sequential tests of Generic, Cortex, and Mempool platforms #11
• Add issue templates #10
• Minor CI and Readme Improvements #8
• Fix GHCR Link for Docker Build #7
• neureka's ccache id #6
• GitHub-based CI/CD Flow #4
• Generic Softmax Kernel #2
• Port GitLab CI #1

Added

• ChimeraDeployer, currently mainly a placeholder
• Allocate templates for Chimera
• ChimeraPlatform, using appropriate allocation templates and using the generic Parser + Binding for the Add node
• Adder CI test for Chimera
• Install flow for chimera-sdk via Makefile
• DeeployChimeraMath library
• Generic FP32 reduce mean bindings, parser, and template
• New alias list parameter for buffer objects
• New test, also included in the CI pipeline, for the reshape and skip connection situation
• 'shape' parameter handling similar to the 'indices' parameter in the generic reshape template
• Test the correcteness of the memory map generated by the tiler
• Add attribute to VariableBuffer to distinguish I/Os
• Add proper static memory allocation with finite lifetime for I/Os
• The memory allocation visualization now displays the allocation for each level used
• Tutorial section in the documentation
• Guide on using the debug print topology pass and code transformation
• VSCode configuration files for improved IDE support
• Multi-branch GitHub Pages deployment support
• Test for the DebugPrintTopologyPass.
• Test for PrintInputGeneration, PrintOutputGeneration, MemoryAwarePrintInputGeneration, MemoryAwarePrintOutputGeneration
• check for CMAKE variable and fallback to searching for cmake
• tensor name mangling
• identity operation removal
• _unpack_const helper function to NodeParser to allow for node attributes that are direct Constant tensors or direct numpy values
• load_file_to_local in dory_mem as a way to load values directly to a local memory (not ram). needed for copying values from flash to wmem needed for Neureka v2
• Add the documentation.yml workflow to deploy doc pages.
• Improved README with more detailed Getting Started section, a section listing related publications, and a list of supported platforms.
• Schedule a CI run every 6 days at 2AM CET to refresh the cache (it expires after 7 days if unused).
• Add the FloatImmediate AbstractType
• Define fp64, fp32, fp16, and bf16
• Add float binding for the Adder in the Generic platform
• Add a FloatAdder test to the CI for Siracusa and Generic platforms
• Extend testType.py with float tests
• LIMITATION: Current LLVM compiler does not support bfp16 and fp16, these types are commented in the library header
• cMake Flow for the Snitch Cluster
• Added snitch_cluster to Makefile
• New Snitch platform with testing application
• Testrunner for tiled and untiled execution (testRunner_snitch.py, testRunner_tiled_snitch.py)
• Minimal library with CycleCounter and utility function
• Support for single-buffered tiling from L2.
• Parsers, Templates, TypeCheckers, Layers, and TCF for the newly supported operators.
• A code transformation pass to filter DMA cores or compute cores for an ExecutionBlock.
• A code transformation pass to profile an ExecutionBlock.
• Test for single kernels, both with and without tiling.
• Adds the --debug flag to cargo install when installing Banshee to get the possibility of enabling the debug prints.
• New tests for the snitch_cluster platform.
• Add macros to main.c to disable printing and testing (convenient when running RTL simulations).
• gvsoc in the Makefile and dockerfile
• cmake flow for gvsoc
• CI tests regarding Snitch run on GVSOC as well
• Float Support for Constbuffer
• Simple Float GEMM on Generic and PULP
• FP...