-
Notifications
You must be signed in to change notification settings - Fork 2.4k
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
(feat): add support for microsoft.range operator for ONNX frontend #28177
Closed
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Signed-off-by: 11happy <[email protected]>
please, resolve conflicts |
### Details: - Integrated grouped dynamic quantization from onednn - Integrated asymmetric per-token dynamic quantization from onednn - Those are not enabled by default, yet ### Tickets: - 148732, 157869, 157589
…otoolkit#27972) ### Details: - fixed crash happens in minicpm-1b-sft int4 model ### Tickets: - *ticket-id*
Porting: openvinotoolkit#27958 Signed-off-by: sgolebiewski-intel <[email protected]>
**Details:** Run If tests on all platforms **Ticket:** TBD --------- Signed-off-by: Kazantsev, Roman <[email protected]>
### Details: - *replace impl string brdgmm with brgconv* - *add test case* - *remove skip CVS-56143 config, CVS-56143 is already closed* - *remove skip CVS-53578 config, CVS-53578 is already closed* - *use new ticket CVS-157596 to track leftover test case* ### Tickets: - *CVS-156792* --------- Signed-off-by: HU Yuan2 <[email protected]>
…penvinotoolkit#27666) ### Details: - Based on openvinotoolkit#27304, should be reviewed after it. ### Tickets: - *152690*
…nvinotoolkit#27979) To filter out automatically picking unwanted custom release builds like https://storage.openvinotoolkit.org/repositories/openvino/packages/2024.5/windows_vc_mt Test run: https://github.com/openvinotoolkit/openvino_tokenizers/actions/runs/12237578864/job/34133648815?pr=338 (now the regular "windows" package is picked) Signed-off-by: Alina Kladieva <[email protected]>
… last stable commit (openvinotoolkit#27985) There are failures with newer commits, e.g. https://github.com/openvinotoolkit/openvino/actions/runs/12240792041/job/34146426674 --------- Signed-off-by: Alina Kladieva <[email protected]>
### Details: - Fixes in unit tests failures
openvinotoolkit#26239) ### Details: 1. Introduce the following operations to the internal opset * `FullyConnected` (`MatMul` with transposed constant second input) * `FullyConnectedCompressed` (`FullyConnected` with weights compression) * `FullyConnectedQuantizedLegacy` (`FullyConnected` with quantized activations and weights and dequantize scale and zero point pulled through the Op by LPT) * `FullyConnectedQuantized` (`FullyConnected` with quantization scales and zero points on activation, weights and outputs). Planned to be used in scope of dynamic quantization. Can be used for a static quantization as well in the future. * Unused inputs are presented as `Constant` input with `Shape{0}` 2. The following transformations were added / updated: * `ConvertFullyConnectedToFullyConnectedCompressed` (replaces proprietary ~`FuseFCAndWeightsDecompression`~) * `ConvertFCToFCQuantizedLegacy` replaces proprietary ~`FuseConvMatmulFCDeconvAndDQScales`~ * `FullyConnectedBiasFusion` (added into CPU folder for now, needs to be checked and review by GPU team before adaptation to internal opset). Replaces proprietary ~`FuseConvolutionMatMulDeconvAndBias`~ * `ConvertMatMulToFC` updated to use `ov::op::internal:FullyConnected`, planned to be moved to internal opset after review from GPU team ### Todo - [x] Clean up debug code - [x] Clean up extra cmake targets - [x] Perf regression check ### Tickets: - 149923
### Details: - *item1* - *...* ### Tickets: - *ticket-id*
**Details:** It appears since JAX 0.4.36 **Ticket:** 158994 Signed-off-by: Kazantsev, Roman <[email protected]>
### Details: - Replacement for openvinotoolkit#27644 ### Tickets: - CVS-154602 - CVS-157192
### Details: - modify class Profiler, add additional time info dumping ### Tickets: - 157579 Co-authored-by: Ivan Tikhonov <[email protected]>
…imension (openvinotoolkit#27939) NOP-elimination doesn't allow the removal of unnecessary data-movement operations stacked on top of each other if their shapes are dynamic, even though certain cases of dynamic shapes can be covered by NOP-elimination. Allow NOP-elimination for dynamic shapes if they have only the 0th dimension dynamic and other static, making this case compatible for such a fusion. - Tickets: * CVS-158394 Signed-off-by: Andrii Staikov <[email protected]> --------- Signed-off-by: Andrii Staikov <[email protected]>
### Details: Clean-up code - create compiler adapter factory class to create the proper compiler adapter. ### Tickets: - *CVS-158848* Signed-off-by: Bogdan Pereanu <[email protected]>
### Details: - copy `openvino/runtime/op/` to `openvino`. `op/` is not initialized in `openvino/runtime/__init__.py`. Update inits in openvino/runtime/op/ - update rule `src/openvino/runtime/*/ops.py: VNE001,VNE003` in _setup.cfg_ - For opset 1 - 16: - move `runtime/opsetx/ops.py`. - update opsetx inits to import from new ops.py location. - add `runtime/opsetx/ops/__init__.py`. - initialize opsets in openvino init - add imports for opset14-16 to `openvino/runtime/__init__.py` - adds possibility to import opsets directly: ```python import openvino.opset13 as ops param = ops.parameter([10]) ``` or ```python import openvino as ov param = ov.opset13.parameter([10]) ``` ### Tickets: - CVS-129458 --------- Signed-off-by: Alicja Miloszewska <[email protected]>
### Details: - *Fix gws value of resample onnx kernel with fs_b_yx_fsv32 format* ### Tickets: - *158837*
…t#28010) Remove the small ones we probably don't need to track this way
### Details: - Disable swiglu fusion which was removed from the previous PR openvinotoolkit#27831 by accident.. ### Tickets: - *ticket-id*
### Details: - This PR fixes: 1562334, 1559879, 1559863, 1559854, 1559677, 1559879, 1559863 - 1559461 and 1559460 are related to ov::pass::pattern::matcher in `decompose_reduce_scalar_output.cpp` - 1559886 and 1559881 are related to ov::pass::pattern::matcher in `transpose_fusion.cpp` - 1559862 is related to ov::pass::pattern::matcher in `transpose_fusion.cpp` - 1559698 and 1559691 are related to ov::pass::pattern::matcher in `bcast_and_pad_zp_buffers.cpp` - all member variables are initialized in the constructors' initializer lists of `ov::pass::pattern::matcher` to address 1559461, 1559460, 1559886, 1559881, 1559862, 1559698, 1559691. ### Tickets: - [*CVS-153064*](https://jira.devtools.intel.com/browse/CVS-153064) - CVS-145082 --------- Co-authored-by: Pavel Durandin <[email protected]>
The first draft to review.
…ic (openvinotoolkit#27988) ### Details: - GPU with systolic does not need FC scaling - GPU with systolic does not support kv cache compresssion yet
github-actions
bot
added
category: CPU
OpenVINO CPU plugin
category: build
OpenVINO cmake script / infra
category: Python API
OpenVINO Python bindings
category: transformations
OpenVINO Runtime library - Transformations
category: LP transformations
OpenVINO Low Precision transformations
category: samples
OpenVINO Runtime Samples
category: IR FE
OpenVINO IR v10 / v11 FrontEnd
category: CI
OpenVINO public CI
category: docs
OpenVINO documentation
category: tools
OpenVINO C++ / Python tools
category: TEMPLATE
OpenVINO Template plugin
category: dependency_changes
Pull requests that update a dependency file
category: AUTO
OpenVINO AUTO device selection plugin
category: PDPD FE
OpenVINO PaddlePaddle FrontEnd
category: TF FE
OpenVINO TensorFlow FrontEnd
category: CPP API
OpenVINO CPP API bindings
category: AUTO BATCH
OpenVINO Auto Batch plugin
github_actions
Pull requests that update GitHub Actions code
category: PyTorch FE
OpenVINO PyTorch Frontend
category: TFL FE
OpenVINO TensorFlow Lite FrontEnd
category: JS API
OpenVino JS API Bindings
no-match-files
category: docs_snippets
OpenVINO docs snippets (docs/snippets)
category: NPU
OpenVINO NPU plugin
category: dockerfiles
category: JAX FE
OpenVINO JAX FrontEnd
category: OVC
OVC tool
category: NPUW
NPUW plugin
labels
Dec 23, 2024
I mistakenly messed the rebase, I will close it and create a fresh PR. |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Labels
category: AUTO BATCH
OpenVINO Auto Batch plugin
category: AUTO
OpenVINO AUTO device selection plugin
category: build
OpenVINO cmake script / infra
category: CI
OpenVINO public CI
category: Core
OpenVINO Core (aka ngraph)
category: CPP API
OpenVINO CPP API bindings
category: CPU
OpenVINO CPU plugin
category: dependency_changes
Pull requests that update a dependency file
category: dockerfiles
category: docs_snippets
OpenVINO docs snippets (docs/snippets)
category: docs
OpenVINO documentation
category: GPU
OpenVINO GPU plugin
category: IE Tests
OpenVINO Test: plugins and common
category: inference
OpenVINO Runtime library - Inference
category: IR FE
OpenVINO IR v10 / v11 FrontEnd
category: JAX FE
OpenVINO JAX FrontEnd
category: JS API
OpenVino JS API Bindings
category: LP transformations
OpenVINO Low Precision transformations
category: NPU
OpenVINO NPU plugin
category: NPUW
NPUW plugin
category: ONNX FE
OpenVINO ONNX FrontEnd
category: OVC
OVC tool
category: PDPD FE
OpenVINO PaddlePaddle FrontEnd
category: Python API
OpenVINO Python bindings
category: PyTorch FE
OpenVINO PyTorch Frontend
category: samples
OpenVINO Runtime Samples
category: TEMPLATE
OpenVINO Template plugin
category: TF FE
OpenVINO TensorFlow FrontEnd
category: TFL FE
OpenVINO TensorFlow Lite FrontEnd
category: tools
OpenVINO C++ / Python tools
category: transformations
OpenVINO Runtime library - Transformations
ExternalPR
External contributor
github_actions
Pull requests that update GitHub Actions code
no-match-files
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Overview:
This pull request fixes #17575 .
Dependencies:
CC: