New build v2 #1
Merged
New build v2 #1
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
### Details: - By PR(openvinotoolkit#22245), `clamp_fp16_output` opt pass was moved to ngraph - Because nodes such as eltwise(`Add`, `Subtract`, `Multiply`, `Divide`) that were fused into target node `gemm` are not supported in pattern, corresponding pattern was extended for this purpose ### Tickets: - 135060
…olkit#22677) ### Details: - *item1* - *...* Add aten::mv operator close openvinotoolkit#22073 ### Tickets: - *ticket-id* --------- Co-authored-by: Ekaterina Aidova <ekaterina.aidova@intel.com> Co-authored-by: Michal Lukaszewski <michal.lukaszewski@intel.com>
### Details: - Remove NGraphFunctions namespace ### Tickets: - CVS-133379
…l attributes (openvinotoolkit#23530) ### Details: - extend the `util::DictAttributeSerializer::on_adapter()` method, making it compatible with `ov::PartialShape` and `ov::op::util::Variable` types; - add extra tests to test the correctness of `Node.get_attributes()` ### Tickets: - openvinotoolkit#23455 --------- Co-authored-by: Jan Iwaszkiewicz <jan.iwaszkiewicz@intel.com>
…openvinotoolkit#23610) ### Tickets: - 136298 - 136163
…nvinotoolkit#23527) ### Closes [openvinotoolkit#23328 ](openvinotoolkit#23328) ### Details: - Support aten::bucketize for pytorch models
…envinotoolkit#23630) ### Details: Move ConvertConvertPromoteTypes transformation from Common to MOC ### Tickets: N/A
…runtime f16 support check (openvinotoolkit#22992) Inherited from openvinotoolkit#22437 --------- Co-authored-by: Ilya Lavrenov <ilya.lavrenov@intel.com>
…t#23628) ### Details: - Significantly reduced amount of using RAM while testing - May introduce test regression in multi-worker scenario (-n auto), but it isn't detected while validation ### Tickets: - 129958
…on-ASCII sentences (openvinotoolkit#23641) **Details:** Add testing non-ASCII sentences for StringLower operation. Needs to be merged after openvinotoolkit/openvino_tokenizers#80. **Ticket:** 135752 --------- Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
### Details: - dev_api `ov::DimensionTracker` and `ov::TableOfEquivalence` classes deleted, logic moved to `ov::Symbol` which is now stored by `ov::Dimension` - new implementation moves responsibility to store and report relations between Symbols directly to the Symbol object. Hence, there is no need for `ov::TableOfEquivalence` and no need for synchronization point anymore. - Equivalence is being tracked by using [Disjoint-set_data_structure](https://en.wikipedia.org/wiki/Disjoint-set_data_structure) which uses less memory than previous implementation.   ### Tickets: - *CVS-133123*
### Details: Removed code that makes friendly names unique from Serialization and a name uniqueness check from Deserializator. Enabled the mode of ResolveNameCollisions transformation to uniqueize all friendly names, not only autogenerated in Frontends ### Tickets: - *CVS-131567* --------- Co-authored-by: Evgenya Nugmanova <evgeniia.nugmanova@intel.com> Co-authored-by: Andrei Kochin <andrei.kochin@intel.com>
### Details: - *fix coverity scan issue1540833 and issue1540832* ### Tickets: - *ticket-id*
…oolkit#23638) ### Details: - The FC changes made in scope of openvinotoolkit#20486 were missed when rebasing openvinotoolkit#20718 - The context is: Even the system and the node does support bf16 precision we have to fall back to f32 in/out precision due to lack of support for decompression with bf16 avx2_vnni_2 in oneDNN fork. - To cover this limitation an additional type mapping parameter in form of std::function was introduced for disabling particular type mapping entry using a runtime check (isa support in this case) ### Tickets: - 122347 - 136163
New cmake fails to be imported in our Android environment --------- Co-authored-by: Mikhail Ryzhov <mikhail.ryzhov@intel.com>
### Details: - *Support lightglue* - *Support int64 as scalar in PyTorch Frontend* ### Tickets: - *CVS-127326, CVS-134328*
### Details: Add a check for input shapes compatibility to the custom CPU matmul shape inference subroutine.
…#23340) ### Details: - *cpu pp_kernel creation will fail for some gemm_convolution + binary post_op cases* - *OneDNN fork pr: openvinotoolkit/oneDNN#236 ### Tickets: - *134839*
### Details: - *[CPU] [AARCH64] jit sigmoid* ### Tickets: - *CVS-133071*
…vinotoolkit#23550) ### Details: - *The first infer request for stable diffusion model might create Tensor with shape and size 0, it must be handled to avoid attempt to reshape array of size 1 into 0 shape* --------- Co-authored-by: Jan Iwaszkiewicz <jan.iwaszkiewicz@intel.com>
…lkit#23504) ### Details: - *use logger to print the logs in dynamo bindings.* - *Add a warning of the case that openvino_execute fails when building OpenVINOGraphModule* ### Tickets: - *No ticket id* ### Description Some modules of dynamo bindings of openvino use `print` directly to print logs. I think it will be better if using `logging` to allow control of the logs. --------- Co-authored-by: Maxim Vafin <maxim.vafin@intel.com>
… API (openvinotoolkit#23338) ### Details: - Implement Core.setProperty() - Implement Core.getProperty() ### Tickets: - 134824 --------- Co-authored-by: Pawel Raasz <pawel.raasz@intel.com>
### Details: - *add new axis mode* ### Tickets: - *CVS-105897, CVS-129991*
### Tickets: - *[CVS-136535](https://jira.devtools.intel.com/browse/CVS-136535)*
…penvinotoolkit#23634) ### Details: - *Fixed the cause of sporadic accuracy drops on several models on dGPU* ### Tickets: - [*CVS-134878*](https://jira.devtools.intel.com/browse/CVS-134878)
…g bf16 (openvinotoolkit#23620) ### Details: - *Use specific kernel for 2d f32 to bf16 conversion instead of multiple calls to cpu_convert* - there is an invocation of parallel_for inside cpu_convert, when copying count is small such as only a head size: 128, each core will only copy ~2 elements if core number is 60, this will result false sharing. The cost can reduce from ~1700ms to ~860ms after the fix. SDPA path will copy a block of heads such as 32*128, so it will not easily be impacted but very small prompt size should also suffer from the problem. - *Change the loop order from B,H,L to B,L,H due to the physical layout, can reduce the cost from ~860ms to ~830ms.* - *Changes in vLLM: ilya-lavrenov/vllm#15 ### Tickets: - *ticket-id*
### Details: - *Import ModuleExtension under try-except* ### Tickets: - *ticket-id*
### Details: - Optimize gemm_tiled_opt kernel for large matmul in dynamic shape execution by 1) increase n tile size and 2) apply manual software pipelining with A matrix prefetch. - Also fixed issues in fused eltwise input data loading for vector data. ### Tickets: - 133445
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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.
Details:
Tickets: