tenstorrent/tt-mlir
May 2025 – Mar 2026
6 Months active
Languages Used
C++MLIRPython
Technical Skills
Device ManagementEmbedded SystemsCode GenerationCode RefactoringCompiler DevelopmentDialect Conversion
Andjela Milovanovic
PROFILE
Andjela Milovanovic
Aleksandar Milovanovic contributed to the tenstorrent/tt-mlir repository by developing and refining Python code generation pipelines, focusing on the EmitPy dialect for translating MLIR representations into executable Python. Over six months, Aleksandar implemented features such as dictionary-based constant caching, global variable management, and conditional execution support, using C++, MLIR, and Python. His work included integrating EmitPy with TTNN for model translation, optimizing device initialization, and enhancing caching mechanisms to improve runtime efficiency and maintainability. The engineering demonstrated depth in compiler design and data structures, resulting in robust, test-driven solutions that streamlined model deployment and code emission workflows.
Overall Statistics
Feature vs Bugs
89%Features
Repository Contributions
14Total
Bugs
1
Commits
14
Features
8
Lines of code
11,899
Activity Months6
Your Network
438 peopleWork History
March 2026
6 Commits • 3 Features
Mar 1, 2026Month: 2026-03 – Delivered core EmitPy/TTCore enhancements across the tenstorrent/tt-mlir project, focusing on conditional execution, flexible dictionary support, and architecture-friendly codegen improvements. These changes improve business value by enabling more expressive models, robust caching, and faster, more maintainable emission pipelines, supported by expanded test coverage.
6 Commits • 3 Features
Mar 1, 2026Month: 2026-03 – Delivered core EmitPy/TTCore enhancements across the tenstorrent/tt-mlir project, focusing on conditional execution, flexible dictionary support, and architecture-friendly codegen improvements. These changes improve business value by enabling more expressive models, robust caching, and faster, more maintainable emission pipelines, supported by expanded test coverage.
March 2026
January 2026
2 Commits • 2 Features
Jan 1, 2026In January 2026, delivered dictionary-based constant caching in EmitPy by consolidating multiple const-eval globals into a single cache, enabling more efficient caching of constant evaluations and smaller generated Python output. Implemented dictionary ops (CreateDictOp, SetValueForDictKeyOp, GetValueForDictKeyOp) to support this caching and introduced consolidated cache usage in the EmitPy flow. Simplified global variable handling by removing the redundant GetGlobalOp in favor of GlobalStatementOp, with updated tests. These changes reduce boilerplate, improve maintainability, and lay groundwork for future performance gains in constant evaluation.
January 2026
2 Commits • 2 Features
Jan 1, 2026In January 2026, delivered dictionary-based constant caching in EmitPy by consolidating multiple const-eval globals into a single cache, enabling more efficient caching of constant evaluations and smaller generated Python output. Implemented dictionary ops (CreateDictOp, SetValueForDictKeyOp, GetValueForDictKeyOp) to support this caching and introduced consolidated cache usage in the EmitPy flow. Simplified global variable handling by removing the redundant GetGlobalOp in favor of GlobalStatementOp, with updated tests. These changes reduce boilerplate, improve maintainability, and lay groundwork for future performance gains in constant evaluation.
November 2025
2 Commits • 1 Features
Nov 1, 2025November 2025 monthly summary for tenstorrent/tt-mlir: Delivered substantial feature work around Python interop and consteval performance. Implemented new EmitPy dialect operations to manage global variables with defined create/access/assign semantics, and added comprehensive tests. Introduced a caching mechanism for consteval results via LoadCachedOp using GlobalOps, with an updated conversion pattern to create and reuse global variables for caching. Expanded test coverage and ensured robust behavior across positive/negative scenarios. Result: improved runtime efficiency for consteval calls and stronger integration with Python workflows.
2 Commits • 1 Features
Nov 1, 2025November 2025 monthly summary for tenstorrent/tt-mlir: Delivered substantial feature work around Python interop and consteval performance. Implemented new EmitPy dialect operations to manage global variables with defined create/access/assign semantics, and added comprehensive tests. Introduced a caching mechanism for consteval results via LoadCachedOp using GlobalOps, with an updated conversion pattern to create and reuse global variables for caching. Expanded test coverage and ensured robust behavior across positive/negative scenarios. Result: improved runtime efficiency for consteval calls and stronger integration with Python workflows.
November 2025
September 2025
1 Commits • 1 Features
Sep 1, 2025Month: 2025-09 — Focused on enabling Python code generation for ResNet models via EmitPy integration in the tt-mlir repository. Key work includes integrating a TTNN to EmitPy emitter and expanding operation coverage to translate more complex models, laying groundwork for future optimizer support. This work strengthens the bridge between model definitions and executable Python pipelines, accelerating deployment of ResNet-style architectures. No major bugs reported or fixed in this period.
September 2025
1 Commits • 1 Features
Sep 1, 2025Month: 2025-09 — Focused on enabling Python code generation for ResNet models via EmitPy integration in the tt-mlir repository. Key work includes integrating a TTNN to EmitPy emitter and expanding operation coverage to translate more complex models, laying groundwork for future optimizer support. This work strengthens the bridge between model definitions and executable Python pipelines, accelerating deployment of ResNet-style architectures. No major bugs reported or fixed in this period.
July 2025
2 Commits • 1 Features
Jul 1, 2025July 2025 monthly summary for tenstorrent/tt-mlir. Key features delivered include the EmitPy Python code generation (MLIR dialect) for the MNIST TTIR pipeline, introducing the EmitPy dialect to encode Python syntax within MLIR and enabling direct Python code emission. This work includes a complete TTIR -> EmitPy conversion pipeline and a subsequent Python code emission step for the MNIST model. Additionally, TTNN-to-EmitPy conversion was refactored to use the EmitPyTTNNEmitter, consolidating the conversion pathway and improving maintainability.
2 Commits • 1 Features
Jul 1, 2025July 2025 monthly summary for tenstorrent/tt-mlir. Key features delivered include the EmitPy Python code generation (MLIR dialect) for the MNIST TTIR pipeline, introducing the EmitPy dialect to encode Python syntax within MLIR and enabling direct Python code emission. This work includes a complete TTIR -> EmitPy conversion pipeline and a subsequent Python code emission step for the MNIST model. Additionally, TTNN-to-EmitPy conversion was refactored to use the EmitPyTTNNEmitter, consolidating the conversion pathway and improving maintainability.
July 2025
May 2025
1 Commits
May 1, 2025Month 2025-05: Improved device initialization reliability in tenstorrent/tt-mlir by fixing the default L1 small size to 32 KB (1 << 15). This correction ensures alignment with the tt-mlir runtime configuration and prevents 0-sized defaults during device opening in the ttnn-standalone workflow. Result: more stable startup, fewer initialization failures, and smoother end-to-end workloads. Commit reference: 8b9e965d48b528808203515ed398ef777902676b (Fix set default l1 small size on opening the device, ##3214).
May 2025
1 Commits
May 1, 2025Month 2025-05: Improved device initialization reliability in tenstorrent/tt-mlir by fixing the default L1 small size to 32 KB (1 << 15). This correction ensures alignment with the tt-mlir runtime configuration and prevents 0-sized defaults during device opening in the ttnn-standalone workflow. Result: more stable startup, fewer initialization failures, and smoother end-to-end workloads. Commit reference: 8b9e965d48b528808203515ed398ef777902676b (Fix set default l1 small size on opening the device, ##3214).
Activity
Loading activity data...
Quality Metrics
Correctness95.8%
Maintainability85.8%
Architecture92.8%
Performance84.4%
AI Usage35.8%
Skills & Technologies
Programming Languages
C++MLIRPython
Technical Skills
C++C++ developmentCode GenerationCode RefactoringCompiler DesignCompiler DevelopmentData StructuresDevice ManagementDialect ConversionDialect DesignEmbedded SystemsEmitPyMLIRPythonPython Development
Repositories Contributed To
Overview of all repositories you've contributed to across your timeline