Search
Sort Score
Result 10 results
Languages All
Labels All
Results 21 - 30 of 93 for

aspose.llm

(0.76 sec)

  1. Custom preset|Documentation

    Customize a built-in Aspose.llm for .NET preset or build one from scratch — three patterns for bringing your own parameters or your own GGUF model.... using Aspose.LLM ; using Aspose.LLM.Abstractions.Parameters...Presets ; var license = new Aspose . LLM . License (); license ....

    docs.aspose.com/llm/net/use-cases/custom-preset/
    more..

  2. Batch processing of text or images - Free Suppo...

    I have a potential project for processing some data using LLM. It is very timely that AsposeLLM was announced. I spent a bit of time playing with it and ran into one issue. I’m unable to clear vram between items I’m proc…...processing of text or images Aspose.LLM Product Family NPozdniakov...

    forum.aspose.com/t/batch-processing-of-text-or-...
    more..

  3. Batch processing|Documentation

    Run many prompts through one loaded Aspose.llm model — amortize the load cost, pick session-per-prompt vs shared-session patterns.... using Aspose.LLM ; using Aspose.LLM.Abstractions.Parameters...Presets ; var license = new Aspose . LLM . License (); license ....

    docs.aspose.com/llm/net/use-cases/batch-process...
    more..

  4. Session persistence|Documentation

    Save and load chat sessions with Aspose.llm for .NET — file format, what is preserved, and parameter behavior on load....persistence Contents [ Hide ] Aspose.LLM for .NET can serialize an...workflow using Aspose.LLM ; using Aspose.LLM.Abstractions.Parameters...

    docs.aspose.com/llm/net/developer-reference/ses...
    more..

  5. GPU deployment with CUDA|Documentation

    Deploy Aspose.llm for .NET on NVIDIA GPUs — select CUDA, offload all layers, configure multi-GPU split, and size VRAM for model + KV cache....is the fastest backend for Aspose.LLM for .NET on NVIDIA hardware...model on it. using Aspose.LLM ; using Aspose.LLM.Abstractions.Acceleration...

    docs.aspose.com/llm/net/use-cases/gpu-deploymen...
    more..

  6. Engine parameters|Documentation

    Configure engine-wide defaults in Aspose.llm for .NET — model cache path, debug logging, log file location, and default thread count....Class reference namespace Aspose.LLM.Core.DependencyInjection...// default: <LocalAppData>/Aspose.LLM/models public bool EnableDebugLogging...

    docs.aspose.com/llm/net/developer-reference/par...
    more..

  7. GPU not detected|Documentation

    Aspose.llm for .NET runs on CPU when you expected GPU — diagnose driver, acceleration selection, binary mismatch, GpuLayers setting....nvidia-smi does not list the Aspose.LLM process. rocm-smi shows zero...GPU. Fix by forcing: using Aspose.LLM.Abstractions.Acceleration...

    docs.aspose.com/llm/net/troubleshooting/gpu-not...
    more..

  8. Simple chat|Documentation

    Send messages to Aspose.llm for .NET without managing sessions yourself — the engine creates and tracks a session implicitly....Minimal example using Aspose.LLM ; using Aspose.LLM.Abstractions.Parameters...Presets ; var license = new Aspose . LLM . License (); license ....

    docs.aspose.com/llm/net/use-cases/simple-chat/
    more..

  9. System requirements|Documentation

    Supported .NET runtimes, operating systems, CPU and GPU requirements, and disk/RAM sizing for Aspose.llm for .NET....system, and hardware for your Aspose.LLM for .NET deployment. Requirements... Supported .NET runtimes Aspose.LLM targets .NET Standard 2.0...

    docs.aspose.com/llm/net/system-requirements/
    more..

  10. Supported acceleration|Documentation

    Hardware acceleration backends supported by Aspose.llm for .NET — CUDA, HIP, Metal, Vulkan, and CPU — with a platform × backend matrix....acceleration Contents [ Hide ] Aspose.LLM for .NET ships native llama...

    docs.aspose.com/llm/net/product-overview/suppor...
    more..