Skip to content

Pull requests: openvinotoolkit/openvino.genai

New pull request New
68 Open 2,467 Closed
68 Open 2,467 Closed
Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Loading
Milestones
Filter by milestone
Loading
Reviews
Filter by reviews
No reviews Review required Approved review Changes requested
Assignee
Filter by who’s assigned
Assigned to nobody Loading
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Pull requests list

Remove unused get_model_kv_cache_precision() category: continuous batching Continuous batching
#2750 opened Sep 19, 2025 by Wovchena Loading…
1
[GHA] Shell command built fix category: GHA CI based on Github actions
#2749 opened Sep 19, 2025 by mryzhov Loading…
1
Bump datasets from 3.6.0 to 4.1.1 in /tools/who_what_benchmark category: WWB PR changes WWB dependencies Pull requests that update a dependency file python Pull requests that update python code
#2748 opened Sep 19, 2025 by dependabot bot Loading…
Bump datasets from 3.6.0 to 4.1.1 in /tests/python_tests category: GGUF GGUF file reader category: tests dependencies dependencies Pull requests that update a dependency file python Pull requests that update python code
#2747 opened Sep 19, 2025 by dependabot bot Loading…
[DO NOT MERGE][ONLY FOR TESTING] Updated chat_sample.py to validate StatefulLLMPipeline category: LLM samples GenAI LLM samples do_not_merge do_not_review
#2745 opened Sep 18, 2025 by AsyaPronina Loading…
Using pytest cache instead of ov cache env variable category: continuous batching Continuous batching category: GGUF GGUF file reader category: GHA CI based on Github actions category: LLM LLM pipeline (stateful, static) category: sampling Sampling / Decoding algorithms category: tokenizers Tokenizer class or submodule update category: visual language Visual language pipeline category: whisper Whisper pipeline
#2744 opened Sep 18, 2025 by sgonorov • Draft
@sgonorov
eagle3 cb impl with top-1 proposal category: cmake / build Cmake scripts category: continuous batching Continuous batching category: CPP API Changes in GenAI C++ public headers category: llm_bench Label for tool/llm_bench folder category: LLM samples GenAI LLM samples category: LLM LLM pipeline (stateful, static) category: LoRA Low rank adapters category: sampling Sampling / Decoding algorithms category: speculative decoding Speculative decoding no-match-files
#2740 opened Sep 17, 2025 by songbell Loading…
@Wovchena
12
add_request() to support token_type_ids with prompt category: continuous batching Continuous batching
#2738 opened Sep 17, 2025 by zhaohb Loading…
10
C API: implemented VlmPipeline category: C API category: cmake / build Cmake scripts no-match-files
#2735 opened Sep 16, 2025 by zhaohb Loading…
@Wovchena
34
[VLM] Add nanoLLaVA category: CPP API Changes in GenAI C++ public headers category: GGUF GGUF file reader category: GH Pages Docs Github Pages documentation category: Python API Python API for GenAI category: visual language Visual language pipeline
#2733 opened Sep 15, 2025 by popovaan Loading…
39
[VLMPipeline] Run embed models on GPU when run LM on NPU
#2730 opened Sep 12, 2025 by JohnLeFeng Loading…
5
Allow additional_params for tokenizer decode in TextStreamer category: CPP API Changes in GenAI C++ public headers category: Python API Python API for GenAI category: text streamer
#2729 opened Sep 12, 2025 by dkalinowski Loading…
@pavel-esir
5
[llm_bench] Add reranking pipeline category: GGUF GGUF file reader category: llm_bench Label for tool/llm_bench folder
#2728 opened Sep 12, 2025 by sbalandi Loading…
43
chang gpu_block_size to 256 category: continuous batching Continuous batching
#2727 opened Sep 12, 2025 by ceciliapeng2011 • Draft
OPT & Clean code of openvino_vision_embeddings_merger_model inputs processing category: visual language Visual language pipeline
#2726 opened Sep 12, 2025 by zhaixuejun1993 Loading…
@Wovchena @peterchen-intel
9
WWB Text Generation with LoRA category: WWB PR changes WWB
#2723 opened Sep 11, 2025 by likholat Loading…
17
Expose get_original_chat_template method in Tokenizer category: CPP API Changes in GenAI C++ public headers category: GHA CI based on Github actions category: Python API Python API for GenAI category: tokenizers Tokenizer class or submodule update
#2722 opened Sep 11, 2025 by mzegla Loading…
7
Bump langchain-core from 0.3.75 to 0.3.76 in /tests/python_tests category: GGUF GGUF file reader category: tests dependencies dependencies Pull requests that update a dependency file python Pull requests that update python code
#2721 opened Sep 11, 2025 by dependabot bot Loading…
Use model path property for caching category: continuous batching Continuous batching
#2720 opened Sep 11, 2025 by praasz Loading…
1
@Wovchena
5
Fixture-based VLM models reusing category: GGUF GGUF file reader category: visual language Visual language pipeline
#2719 opened Sep 10, 2025 by sgonorov Loading…
@sgonorov
19
Bump minja with call blocks support, remove chat template fallback for MiniCPM3-4B category: cmake / build Cmake scripts category: tokenizers Tokenizer class or submodule update
#2718 opened Sep 10, 2025 by yatarkan Loading…
1
Text2Image pipeline export/import category: CPP API Changes in GenAI C++ public headers category: Image generation samples GenAI Image generation samples category: image generation Image generation pipelines category: Python API Python API for GenAI do_not_merge no-match-files
#2716 opened Sep 9, 2025 by as-suvorov Loading…
17
Enable CDPruner category: cmake / build Cmake scripts category: continuous batching Continuous batching category: CPP API Changes in GenAI C++ public headers category: llm_bench Label for tool/llm_bench folder category: Python API Python API for GenAI category: sampling Sampling / Decoding algorithms category: visual language Visual language pipeline category: VLM samples GenAI VLM samples no-match-files
#2714 opened Sep 9, 2025 by yangwang201911 • Draft
[DO NOT MERGE][FOR VALIDATION] Extended a bit speculative_decoding_lm.py sample to show the whole pipeline throughput category: LLM samples GenAI LLM samples
#2713 opened Sep 8, 2025 by AsyaPronina Loading…
Enable VLM lookup. category: continuous batching Continuous batching category: prompt lookup Prompt look-up decoding category: speculative decoding Speculative decoding category: visual language Visual language pipeline no-match-files
#2707 opened Sep 5, 2025 by xipingyan Loading…
31
ProTip! Follow long discussions with comments:>50.