NVIDIA/TensorRT-Incubator
Experimental projects related to TensorRT
30 Releases
Latest: 2mo ago
tripy-v0.1.7Latest
![github-actions[bot]](https://avatars.githubusercontent.com/in/15368?v=4){kind=small}
github-actions[bot]·2mo ago·March 25, 2026📋 What's Changed
- Fixes L1 and release pipelines by @pranavm-nvidia in https://github.com/NVIDIA/TensorRT-Incubator/pull/830
- Fixes various minor issues in the release pipeline by @pranavm-nvidia in https://github.com/NVIDIA/TensorRT-Incubator/pull/831
- Adds skills and various code improvements by @pranavm-nvidia in https://github.com/NVIDIA/TensorRT-Incubator/pull/832
- Full Changelog: https://github.com/NVIDIA/TensorRT-Incubator/compare/tripy-v0.1.6...tripy-v0.1.7
tripy-v0.1.6
github-actions[bot]·2mo ago·March 20, 2026📋 What's Changed
- build llvm package CI/CD by @lanluo-nvidia in https://github.com/NVIDIA/TensorRT-Incubator/pull/823
- Updates various dependencies, Python 3.11 fixes, adds release container by @pranavm-nvidia in https://github.com/NVIDIA/TensorRT-Incubator/pull/820
- [compiler] Add NVTX range annotations for JAX subgraph profiling by @shelkesagar29 in https://github.com/NVIDIA/TensorRT-Incubator/pull/824
- add cmake flag to support build with pre-built llvm by @lanluo-nvidia in https://github.com/NVIDIA/TensorRT-Incubator/pull/826
- Add project documentation for TensorRT dialect and StableHLO compiler by @christopherbate in https://github.com/NVIDIA/TensorRT-Incubator/pull/828
- Breaks reference cycles for Executable outputs to prevent memory growth by @pranavm-nvidia in https://github.com/NVIDIA/TensorRT-Incubator/pull/827
- Updates version to 0.1.6 by @pranavm-nvidia in https://github.com/NVIDIA/TensorRT-Incubator/pull/829
- Full Changelog: https://github.com/NVIDIA/TensorRT-Incubator/compare/llvm-packages-aarch64-d6e2143b064e62458eb210394e623bc0abeb266b...tripy-v0.1.6
📋 What's Changed
- build llvm package CI/CD by @lanluo-nvidia in https://github.com/NVIDIA/TensorRT-Incubator/pull/823
- Updates various dependencies, Python 3.11 fixes, adds release container by @pranavm-nvidia in https://github.com/NVIDIA/TensorRT-Incubator/pull/820
- [compiler] Add NVTX range annotations for JAX subgraph profiling by @shelkesagar29 in https://github.com/NVIDIA/TensorRT-Incubator/pull/824
- add cmake flag to support build with pre-built llvm by @lanluo-nvidia in https://github.com/NVIDIA/TensorRT-Incubator/pull/826
- Add project documentation for TensorRT dialect and StableHLO compiler by @christopherbate in https://github.com/NVIDIA/TensorRT-Incubator/pull/828
- Breaks reference cycles for Executable outputs to prevent memory growth by @pranavm-nvidia in https://github.com/NVIDIA/TensorRT-Incubator/pull/827
- Updates version to 0.1.6 by @pranavm-nvidia in https://github.com/NVIDIA/TensorRT-Incubator/pull/829
- Full Changelog: https://github.com/NVIDIA/TensorRT-Incubator/compare/llvm-packages-aarch64-d6e2143b064e62458eb210394e623bc0abeb266b...tripy-v0.1.6
llvm-packages-x86_64-d6e2143b064e62458eb210394e623bc0abeb266bPre-release
github-actions[bot]·3mo ago·March 3, 2026llvm-packages-aarch64-d6e2143b064e62458eb210394e623bc0abeb266bPre-release
github-actions[bot]·3mo ago·March 3, 2026tripy-v0.1.5
github-actions[bot]·3mo ago·February 19, 2026📋 What's Changed
- Updates version to 0.1.5 by @pranavm-nvidia in https://github.com/NVIDIA/TensorRT-Incubator/pull/810
- Full Changelog: https://github.com/NVIDIA/TensorRT-Incubator/compare/mlir-tensorrt-v0.4.9...tripy-v0.1.5
mlir-tensorrt-v0.4.9
github-actions[bot]·3mo ago·February 19, 2026📋 What's Changed
- [compiler] Update Softmax matcher used in stablehlo-to-tensorrt by @shelkesagar29 in https://github.com/NVIDIA/TensorRT-Incubator/pull/808
- [python] Force initialization of tvm_ffi in the mlir_tensorrt_runtime package by @christopherbate in https://github.com/NVIDIA/TensorRT-Incubator/pull/809
- Full Changelog: https://github.com/NVIDIA/TensorRT-Incubator/compare/mlir-tensorrt-v0.4.7.dev202602180...mlir-tensorrt-v0.4.9
mlir-tensorrt-v0.4.7.dev202602180
github-actions[bot]·3mo ago·February 18, 2026📋 What's Changed
- Fix the wheel dependency issue in thor by @lanluo-nvidia in https://github.com/NVIDIA/TensorRT-Incubator/pull/790
- Integrate internal changes by @christopherbate in https://github.com/NVIDIA/TensorRT-Incubator/pull/807
- Full Changelog: https://github.com/NVIDIA/TensorRT-Incubator/compare/mlir-tensorrt-v0.4.6.dev202601290...mlir-tensorrt-v0.4.7.dev202602180
mlir-tensorrt-v0.4.6.dev202601290Pre-release
github-actions[bot]·4mo ago·January 30, 2026📋 What's Changed
- [executor] Add support for "packed" calling convention for ABI V1 by @christopherbate in https://github.com/NVIDIA/TensorRT-Incubator/pull/798
- [integrations/python] Revert accidental changes to package setup and TOML files by @christopherbate in https://github.com/NVIDIA/TensorRT-Incubator/pull/799
- [compiler] Attempt to fix flaky 'end-to-end-binary' test by @christopherbate in https://github.com/NVIDIA/TensorRT-Incubator/pull/800
- Full Changelog: https://github.com/NVIDIA/TensorRT-Incubator/compare/mlir-tensorrt-v0.4.6.dev202601230...mlir-tensorrt-v0.4.6.dev202601290
mlir-tensorrt-v0.4.6.dev202601230
github-actions[bot]·4mo ago·January 24, 2026📋 What's Changed
- [cmake] Fix handling of LLVM_DEFINITIONS by @christopherbate in https://github.com/NVIDIA/TensorRT-Incubator/pull/789
- integrate internal changes by @christopherbate in https://github.com/NVIDIA/TensorRT-Incubator/pull/788
- integrate internal changes by @christopherbate in https://github.com/NVIDIA/TensorRT-Incubator/pull/792
- [mlir-tensorrt] NFC: revert accidental change to Version.cmake by @christopherbate in https://github.com/NVIDIA/TensorRT-Incubator/pull/793
- integrate internal changes by @christopherbate in https://github.com/NVIDIA/TensorRT-Incubator/pull/794
- integrate internal changes by @christopherbate in https://github.com/NVIDIA/TensorRT-Incubator/pull/795
- [executor] Add crash reproducer file support in Runtime API by @christopherbate in https://github.com/NVIDIA/TensorRT-Incubator/pull/796
- Full Changelog: https://github.com/NVIDIA/TensorRT-Incubator/compare/mlir-tensorrt-v0.4.6.dev202601140...mlir-tensorrt-v0.4.6.dev202601230
mlir-tensorrt-v0.4.6.dev202601140
github-actions[bot]·5mo ago·January 14, 2026📋 What's Changed
- [integrations/PJRT] Remove 'tensorrt' and 'nvidia-cuda-runtime-cu13' dependencies from pyproject.toml by @christopherbate in https://github.com/NVIDIA/TensorRT-Incubator/pull/786
- Full Changelog: https://github.com/NVIDIA/TensorRT-Incubator/compare/mlir-tensorrt-v0.4.5...mlir-tensorrt-v0.4.6.dev202601140
mlir-tensorrt-v0.4.5
github-actions[bot]·5mo ago·January 13, 2026📋 What's Changed
- Integrate LLVM@d6e2143b064e by @christopherbate in https://github.com/NVIDIA/TensorRT-Incubator/pull/754
- [kernel] Add vector.from_elements unroll patterns to LowerToNVVM by @christopherbate in https://github.com/NVIDIA/TensorRT-Incubator/pull/755
- [compiler] Improve consistency of how 'target' attribute on grouping ops is handled by @christopherbate in https://github.com/NVIDIA/TensorRT-Incubator/pull/756
- [compiler] Move StableHLO partitioning attribute handling to StablehloToPlan pass by @christopherbate in https://github.com/NVIDIA/TensorRT-Incubator/pull/757
- [Plan] Rename cluster ops to shorter mnemonics by @christopherbate in https://github.com/NVIDIA/TensorRT-Incubator/pull/758
- [StablehloExt] Refactor simplification patterns into separate files by @christopherbate in https://github.com/NVIDIA/TensorRT-Incubator/pull/761
- integrate internal changes by @christopherbate in https://github.com/NVIDIA/TensorRT-Incubator/pull/762
- [CI] upgrade release base image from rockylinux8 to rocklinux9 by @lanluo-nvidia in https://github.com/NVIDIA/TensorRT-Incubator/pull/763
- + 22 more
mlir-tensorrt-v0.4.4.dev202512190Pre-release
github-actions[bot]·5mo ago·December 20, 2025✨ Major Features
- Open-source the kernel generation backend
- Open-source the PJRT (XLA/JAX) integration
- Various optimizations targeting StableHLO while loops and raising to for-style loops
- Improve C++ host code generation pipeline; fill in some missing EmitC converters
📦 Generated Release Notes
- Update CI workflows and devcontainer configs for CUDA 12.9 and Ubuntu 24.04 by @christopherbate in https://github.com/NVIDIA/TensorRT-Incubator/pull/723
- migrate internal changes by @christopherbate in https://github.com/NVIDIA/TensorRT-Incubator/pull/722
- migrate internal changes by @christopherbate in https://github.com/NVIDIA/TensorRT-Incubator/pull/724
- [CI] Adding Test Pipeline for PRs by @lanluo-nvidia in https://github.com/NVIDIA/TensorRT-Incubator/pull/725
- [mlir-tensorrt] Migrate internal change by @christopherbate in https://github.com/NVIDIA/TensorRT-Incubator/pull/726
- Add conversion of JAX shape_assertion custom calls to cf.assert by @christopherbate in https://github.com/NVIDIA/TensorRT-Incubator/pull/728
- Add Math dialect to EmitC conversion support by @christopherbate in https://github.com/NVIDIA/TensorRT-Incubator/pull/729
- Refactor: Move StableHLO matchers to dialect utils and reorganize namespaces by @christopherbate in https://github.com/NVIDIA/TensorRT-Incubator/pull/730
- + 23 more
mlir-tensorrt-v0.4.2dev20251112Pre-release
christopherbate·6mo ago·November 22, 2025tripy-v0.1.4
github-actions[bot]·10mo ago·August 21, 2025📋 What's Changed
- [mlir-tensorrt] Raise Normalization for Pytorch (torch-mlir) Layer norm. by @matthewfl in https://github.com/NVIDIA/TensorRT-Incubator/pull/680
- [mlir-tensorrt] Raise activations from their elementwise representation to tensorrt.activation Op by @matthewfl in https://github.com/NVIDIA/TensorRT-Incubator/pull/679
- Migrate internal changes by @christopherbate in https://github.com/NVIDIA/TensorRT-Incubator/pull/687
- Add tensor methods for cast, copy, and shape manipulation ops by @akhilg-nv in https://github.com/NVIDIA/TensorRT-Incubator/pull/688
- [TensorRT] Extract layer metadata from FusedLocation by @yizhuoz004 in https://github.com/NVIDIA/TensorRT-Incubator/pull/689
- Removes a workaround for #496 when no-op functions were not compiled correctly. by @pranavm-nvidia in https://github.com/NVIDIA/TensorRT-Incubator/pull/692
- Adds support for reflect mode in the pad operation by @pranavm-nvidia in https://github.com/NVIDIA/TensorRT-Incubator/pull/696
- Use FusedLocation to hold layer metadata by @yizhuoz004 in https://github.com/NVIDIA/TensorRT-Incubator/pull/690
- + 1 more
✨ New Contributors
- @matthewfl made their first contribution in https://github.com/NVIDIA/TensorRT-Incubator/pull/680
- Full Changelog: https://github.com/NVIDIA/TensorRT-Incubator/compare/tripy-v0.1.3...tripy-v0.1.4
tripy-v0.1.3
github-actions[bot]·10mo ago·August 1, 2025📋 What's Changed
- Add Stable Diffusion demo by @akhilg-nv in https://github.com/NVIDIA/TensorRT-Incubator/pull/100
- Update packages for MLIR-TRT 0.1.43 by @yizhuoz004 in https://github.com/NVIDIA/TensorRT-Incubator/pull/683
- Support `DimensionInputInfo` in tp.compile by @yizhuoz004 in https://github.com/NVIDIA/TensorRT-Incubator/pull/618
- Removes outdated alignment warning by @pranavm-nvidia in https://github.com/NVIDIA/TensorRT-Incubator/pull/684
- Update Tripy v0.1.3 by @yizhuoz004 in https://github.com/NVIDIA/TensorRT-Incubator/pull/685
- Full Changelog: https://github.com/NVIDIA/TensorRT-Incubator/compare/mlir-tensorrt-v0.1.43...tripy-v0.1.3
mlir-tensorrt-v0.1.43
shelkesagar29·10mo ago·July 29, 2025tripy-v0.1.2
github-actions[bot]·1y ago·June 12, 2025📋 What's Changed
- Various improvements to SAMv2 demo by @pranavm-nvidia in https://github.com/NVIDIA/TensorRT-Incubator/pull/646
- Adds an API to set dimension names, updates SAMv2 to trigger MHA fusion by @pranavm-nvidia in https://github.com/NVIDIA/TensorRT-Incubator/pull/657
- Full Changelog: https://github.com/NVIDIA/TensorRT-Incubator/compare/mlir-tensorrt-v0.1.42...tripy-v0.1.2
mlir-tensorrt-v0.1.42
shelkesagar29·1y ago·June 11, 2025mlir-tensorrt-v0.1.41
shelkesagar29·1y ago·May 23, 2025tripy-v0.1.1
github-actions[bot]·1y ago·May 9, 2025📋 What's Changed
- Add `tensorrt_engine` to Executable API by @yizhuoz004 in https://github.com/NVIDIA/TensorRT-Incubator/pull/608
- Fixes various issues in L1 tests, improves reliability of SAMv2 downl… by @pranavm-nvidia in https://github.com/NVIDIA/TensorRT-Incubator/pull/610
- Switches `serialized_tensorrt_engine` to a property by @pranavm-nvidia in https://github.com/NVIDIA/TensorRT-Incubator/pull/612
- Add support for TensorRT Quickly Deployable Plugins by @samurdhikaru in https://github.com/NVIDIA/TensorRT-Incubator/pull/578
- Simplifies silu, updates executables to reject tensors that are not GPU constants by @pranavm-nvidia in https://github.com/NVIDIA/TensorRT-Incubator/pull/614
- Reorders guides to make them flow more logically by @pranavm-nvidia in https://github.com/NVIDIA/TensorRT-Incubator/pull/615
- Implements various features/quality of life improvements to enable YOLO example by @pranavm-nvidia in https://github.com/NVIDIA/TensorRT-Incubator/pull/616
- Updates `compile` to set names for weights in the module by @pranavm-nvidia in https://github.com/NVIDIA/TensorRT-Incubator/pull/621
- + 4 more
✨ New Contributors
- @samurdhikaru made their first contribution in https://github.com/NVIDIA/TensorRT-Incubator/pull/578
- Full Changelog: https://github.com/NVIDIA/TensorRT-Incubator/compare/tripy-v0.1.0...tripy-v0.1.1
tripy-v0.1.0
github-actions[bot]·1y ago·April 10, 2025📋 What's Changed
- Adds package index links for MLIR-TRT 0.1.40 by @pranavm-nvidia in https://github.com/NVIDIA/TensorRT-Incubator/pull/605
- Migrates Tripy to use the tensorrt dialect instead of StableHLO by @pranavm-nvidia in https://github.com/NVIDIA/TensorRT-Incubator/pull/607
- Full Changelog: https://github.com/NVIDIA/TensorRT-Incubator/compare/mlir-tensorrt-v0.1.40...tripy-v0.1.0
milr-tensorrt-v0.1.40mlir-tensorrt-v0.1.40
shelkesagar29·1y ago·April 8, 2025Supports TensorRT 10.9.0.34
mlir-tensorrt-v0.1.39
shelkesagar29·1y ago·April 3, 2025tripy-v0.0.10
github-actions[bot]·1y ago·January 28, 2025📋 What's Changed
- Pins TensorRT to a working version to avoid a segfault in 10.8 by @pranavm-nvidia in https://github.com/NVIDIA/TensorRT-Incubator/pull/483
- Full Changelog: https://github.com/NVIDIA/TensorRT-Incubator/compare/tripy-v0.0.9...tripy-v0.0.10
tripy-v0.0.9
github-actions[bot]·1y ago·January 23, 2025📋 What's Changed
- Reduce nanogpt quantization calib size to speed up test by @yizhuoz004 in https://github.com/NVIDIA/TensorRT-Incubator/pull/461
- Move internal change: [compiler] Add compilation task registry by @christopherbate in https://github.com/NVIDIA/TensorRT-Incubator/pull/465
- Disables container caching to save space by @pranavm-nvidia in https://github.com/NVIDIA/TensorRT-Incubator/pull/466
- Fixes a flaky test by increasing tolerance by @pranavm-nvidia in https://github.com/NVIDIA/TensorRT-Incubator/pull/462
- Tripy eager cache by @farazkh80 in https://github.com/NVIDIA/TensorRT-Incubator/pull/418
- Move internal changes by @shelkesagar29 in https://github.com/NVIDIA/TensorRT-Incubator/pull/468
- Support small and tiny config for SAM2 by @yizhuoz004 in https://github.com/NVIDIA/TensorRT-Incubator/pull/469
- Fix sam2 sample artifact removal by @yizhuoz004 in https://github.com/NVIDIA/TensorRT-Incubator/pull/470
- + 13 more
tripy-v0.0.8
github-actions[bot]·1y ago·December 18, 2024📋 What's Changed
- Run L1 tests serially to prevent OOMs by @pranavm-nvidia in https://github.com/NVIDIA/TensorRT-Incubator/pull/454
- Updates install instructions to point to PyPI by @pranavm-nvidia in https://github.com/NVIDIA/TensorRT-Incubator/pull/453
- Enable contributions from external sources by @pranavm-nvidia in https://github.com/NVIDIA/TensorRT-Incubator/pull/456
- Move internal changes by @christopherbate in https://github.com/NVIDIA/TensorRT-Incubator/pull/455
- Disables pushing benchmark results for forks by @pranavm-nvidia in https://github.com/NVIDIA/TensorRT-Incubator/pull/458
- Full Changelog: https://github.com/NVIDIA/TensorRT-Incubator/compare/tripy-v0.0.7...tripy-v0.0.8
tripy-v0.0.7
github-actions[bot]·1y ago·December 17, 2024📋 What's Changed
- Replace tp.Parameter with tp.Tensor in resnet notebook by @yizhuoz004 in https://github.com/NVIDIA/TensorRT-Incubator/pull/433
- Combine the functionality of the `convert_to_tensors` decorator and the `dtypes` constraint. by @slyubomirsky in https://github.com/NVIDIA/TensorRT-Incubator/pull/420
- Adds explicit notebook tests, updates CI by @pranavm-nvidia in https://github.com/NVIDIA/TensorRT-Incubator/pull/436
- Remove plugin WAR due to mlir-tensorrt issue #915 by @parthchadha in https://github.com/NVIDIA/TensorRT-Incubator/pull/438
- Always construct memref value in storage op by @yizhuoz004 in https://github.com/NVIDIA/TensorRT-Incubator/pull/439
- Move internal changes by @shelkesagar29 in https://github.com/NVIDIA/TensorRT-Incubator/pull/437
- Enable sam2 video pipeline by @parthchadha in https://github.com/NVIDIA/TensorRT-Incubator/pull/444
- Manage peak memory in SAM2 by @parthchadha in https://github.com/NVIDIA/TensorRT-Incubator/pull/449
- + 4 more
tripy-v0.0.6
github-actions[bot]·1y ago·December 9, 2024📋 What's Changed
- [mlir-tensorrt] NFC: update GitHub actions caching config for MLIR-TRT jobs by @christopherbate in https://github.com/NVIDIA/TensorRT-Incubator/pull/430
- Upgrade tripy version to 0.0.6 by @parthchadha in https://github.com/NVIDIA/TensorRT-Incubator/pull/424
- Full Changelog: https://github.com/NVIDIA/TensorRT-Incubator/compare/mlir-tensorrt-v0.1.38...tripy-v0.0.6
MLIR-TensorRT v0.1.38mlir-tensorrt-v0.1.38
shelkesagar29·1y ago·December 6, 2024tripy-v0.0.5
github-actions[bot]·1y ago·November 21, 2024📋 What's Changed
- Add compile fixture to test integration ops with compile mode by @parthchadha in https://github.com/NVIDIA/TensorRT-Incubator/pull/387
- Update mlir-tensorrt dependency version in Tripy by @parthchadha in https://github.com/NVIDIA/TensorRT-Incubator/pull/399
- Full Changelog: https://github.com/NVIDIA/TensorRT-Incubator/compare/tripy-v0.0.4...tripy-v0.0.5