aropb

Background permission and error in windows.create()

14

I am using the "background" permission in the MV3 extension. When the browser is closed, the windows.create() method is called in the tabs.onRemoved event. This works great in Chrome. But...

The release OpenCvSharp 4.10 is ready

12

Hi, We expect very much Sdcb.OpenCvSharp4.mini.runtime's new version. Thanks.

[BUG]: KernelMemory.AskAsync() does not work - exception: object reference not set to an instance of an object

28

### Description I use KernelMemory. LogiBits is empty. The error occurs at the time of the call: memory.AskAsync()  Debug with clone classes: BaseSamplingPipeline, DefaultSamplingPipeline  ### Reproduction Steps The...

### Context / Scenario Hi, The cancellation of the request is not performed in SearchClient.GenerateAnswer(). This place does not provide a response to the cancellation of a long-term request (with...

PaddleOCR and NPU

2

Hi, I have an Intel Core Ultra 9 Processor with NPU. It was not possible to start recognition for the NPU. Everything works for the CPU. This my code: string...

[BUG]: KernelMemory - Simultaneous execution of AskDocument & ImportDocument

18

### Description System.ObjectDisposedException: Cannot access a disposed object. Object name: 'Cannot use this `SafeLLamaContextHandle` - it has been disposed'. at LLama.Native.SafeLLamaContextHandle.ThrowIfDisposed() at LLama.Native.SafeLLamaContextHandle.GetLogitsIth(Int32 i) at LLama.StatelessExecutor.InferAsync(String prompt, IInferenceParams inferenceParams, CancellationToken...

### Description 1. Wherever possible, it is better not to create a Context (this increases the memory used). For example, you can use: weights.Tokenize() Instead of: context.Tokenize() 2. The problem...

[BUG:] When switching to new versions of LLamaSharp 0.16.0, there was a slowdown

30

### Description After upgrading from KM 0.61 and LLamaSharp 0.13 to the latest versions, the processing ImportDocumentAsync/AskAsync speed has significantly decreased, almost 2 times. All settings and equipment are the...

Misc. bug: CUDA errors with multi-threaded use

20

I'm using LLamaSharp 0.21.0 (CUDA 12.8 beckend) with the commit llama.cpp: https://github.com/ggerganov/llama.cpp/commit/5783575c9d99c4d9370495800663aa5397ceb0be Model for Inference (one instance for all users): Qwen2.5-14B-1M-Q5-K-M Model for Embedding (one instance for all users): Qwen2.5-1.5B-Q5-K-M...

Fatal error. 0xC0000005

4

### Describe the bug Fatal error. 0xC0000005 at OpenCvSharp.Internal.NativeMethods.core_mean(IntPtr, IntPtr, OpenCvSharp.Scalar ByRef) at OpenCvSharp.Cv2.Mean(OpenCvSharp.InputArray, OpenCvSharp.InputArray) at OpenCvSharp.Mat.Mean(OpenCvSharp.InputArray) at Sdcb.OpenVINO.PaddleOCR.PaddleOcrDetector.GetScore(OpenCvSharp.Point[], OpenCvSharp.Mat) at Sdcb.OpenVINO.PaddleOCR.PaddleOcrDetector+c__DisplayClass35_0.b__0(OpenCvSharp.Point[]) at System.Linq.Enumerable+ArrayWhereSelectIterator`2[[System.__Canon, System.Private.CoreLib, Version=9.0.0.0, Culture=neutral, PublicKeyToken=7cec85d7bea7798e],[OpenCvSharp.RotatedRect, OpenCvSharp, Version=1.0.0.0,...