#LLamaSharp
LightNews LightNews
devdigest.today
LLamaSharp: Running LLaMA and LLaVA with C#

#devdigest #CSharp
GitHub - SciSharp/LLamaSharp: A C#/.NET library to run LLM (🦙LLaMA/LLaVA) on your local device efficiently.
A C#/.NET library to run LLM (🦙LLaMA/LLaVA) on your local device efficiently. - SciSharp/LLamaSharp
devdigest.today
November 16, 2024 at 4:00 PM
malwareunicorn.bsky.social
Before considering using Llamasharp, know that it pulls in a unmanaged NativeAPI DLL underneath. Make sure you’re doing your library load integrity checking.
May 16, 2025 at 2:28 PM
braidpoint.bsky.social
❓ to the #fsharp community: is anyone working with LlamaSharp? We're scanning the docs/wiki, but are particularly interested in BatchedExecution and grammars definition. It's hard to believe that we'd be the first - unless someone is "secret sauce"-ing it. 😇 scisharp.github.io/LLamaSharp/0...
LLamaSharp Documentation
scisharp.github.io
January 14, 2025 at 10:32 PM
nimblepros.com
❓ Want a local, private RAG Q&A tool in .NET?

💻This walkthrough covers chunking, embeddings, vector stores, and LlamaSharp — all running on your machine!

https://blog.nimblepros.com/blogs/building-rag-dotnet

#AI #dotnet
June 9, 2026 at 12:30 PM
braidpoint.bsky.social
@dsyme.bsky.social 🚧 Just an FYI we've been looking into DiffSharp per your suggestion. Frankly we think everyone in #dotnet should be looking into this for #AI. 🚀 Model tuning on GPU coupled with running with LlamaSharp is a huge opportunity that should wake up #fsharp and #csharp devs.
💙 🐓 🌞
February 12, 2025 at 1:08 PM
philco.bsky.social
I was trying to wrap my head around an issue I think I found with LlamaSharp. Thankfully, they had a suite of examples that I was able to use to debug, all using Spectre.Console. Pretty slick

github.com/SciSharp/LLa...
llama_chat_apply_template best practices? · Issue #1021 · SciSharp/LLamaSharp
Description I was working on some samples using the Stateless Executor, and I kept running into instances where the results were pretty crummy and they'd go off the rails pretty frequently, running...
github.com
December 23, 2024 at 6:54 PM
devdigest.today
Run a Large Language Model(LLM) Like ChatGPT Locally With C#
Run a Large Language Model(LLM) Like ChatGPT Locally With C# - Code Maze
This article will explore how we can use LLamaSharp to run a Large Language Model, or LLM, locally using C#.
devdigest.today
August 12, 2024 at 7:12 AM
dot.net
🚀 Agentic AI in .NET workflows? Yes, please.

✨ TODAY AT 9AM PT, ON .NET ✨
Explore how local-first SLMs like OllamaSharp & LLamaSharp power agentic systems with Semantic Kernel.
See you here ➡️ msft.it/63329t6MUh
#dotnet #SemanticKernel
spot art. Photo of presenter(s). text reads: On .NET Live | Building agentic systems with local-first SLMs
October 27, 2025 at 1:35 PM
codigo-e-costura.bsky.social
eu vi que dava para puxar no llama.. mas to usando a parte web mesmo.. qria testar com o github.com/SciSharp/LLa... ou algo alternativo.. terminando de migrar os imputs aqui eu vou perguntar se tem alguma alternativa para esse llamaSharp

mas ja achei mais rapido.. e as respostas estao melhores..
GitHub - SciSharp/LLamaSharp: A C#/.NET library to run LLM (🦙LLaMA/LLaVA) on your local device efficiently.
A C#/.NET library to run LLM (🦙LLaMA/LLaVA) on your local device efficiently. - SciSharp/LLamaSharp
github.com
January 27, 2025 at 7:49 PM
warlockbill.bsky.social
There are a number of frameworks. GPT4All, LM Studio, Jan, Llama, and Ollama are the ones that come to mind.

It'll also depend on what language you use. For Csharp, LlamaSharp, since you mentioned Unreal.
January 24, 2025 at 1:52 PM
xoofx.mastodon.social.ap.brid.gy
@nietras I'm waiting for the Phi-4 ONNX version to be available (tried optimum to convert and failed installing it). I could go with LLamaSharp but dunno if it is worth it. With which runtime representation do you mostly work with these days?
January 10, 2025 at 7:27 PM
originalcoder.bsky.social
@philco.bsky.social Thank you so much for your work and explanations of LLamaSharp basics. Super helpful!

Would love to collaborate with you on our DAISI project, if you are interested. daisi.ai
DAISI - Distributed AI Systems Inc
DAISI is the fastest and most reliable distributed AI network on the planet.
daisi.ai
November 22, 2025 at 5:27 PM
codigo-e-costura.bsky.social
👉👉👉 LLamaSharp
January 22, 2025 at 12:07 PM
flavio58.bsky.social
The C#/.NET binding of llama.cpp. It provides higher-level APIs to inference the LLaMA Models and deploy it on local device with C#/.NET.
GitHub - SciSharp/LLamaSharp: Run local LLaMA/GPT model easily and fast in C#!🤗 It's also easy to...
Run local LLaMA/GPT model easily and fast in C#!🤗 It's also easy to integrate LLamaSharp with semantic-kernel, unity, WPF and WebApp. - GitHub - SciSharp/LLamaSharp: Run local LLaMA/GPT model e...
github.com
December 29, 2023 at 7:44 PM
imnayan.bsky.social
My private #AI/ #LLM/ #RAG experiment using #Microsoft stack spcly wth

#dotnetaspire #LLamaSharp #Cuda #KernelMemory #SementicKernel #aspire #dotnet 9

May be a vscode ext too. What’s ur view?

github.com/nayanbhagowa...
GitHub - nayanbhagowaty/VISTA: A Microsoft stack to host a local LLM as a private API endpoint for private AI agent
A Microsoft stack to host a local LLM as a private API endpoint for private AI agent - nayanbhagowaty/VISTA
github.com
December 4, 2024 at 9:55 AM
braidpoint.bsky.social
BuffSharp would be a great name! 🦾

Honestly - we're toying with the idea of building a new backend for LlamaSharp to interface with Tenstorrent hardware and the *natural* next Q was "should we do the same with DiffSharp?". So perhaps that will be a natural cleave point for forking and renaming.
February 12, 2025 at 1:59 PM
philco.bsky.social
New blog posts getting into some of the advanced stuff you can do with JSON and GBNF generation with my RedPajama project to help with using LlamaSharp
thirty25.blog/blog/2025/04...

Come see the fancy tabs in person!
May 3, 2025 at 3:29 AM
philco.bsky.social
Another post in my LlamaSharp series.

This time we are building GBNF automatically from c# class declarations
thirty25.blog/blog/2025/04...
Thirty25 - Strongly Typed GBNF Generation
Quite exciting this computer magic
thirty25.blog
April 29, 2025 at 6:39 PM
philco.bsky.social
Continuing my intro to LlamaSharp posts, JSON Generation with LlamaSharp
thirty25.blog/blog/2025/04...

Next step: we get to get weird with GBNF generation
Thirty25 - JSON Generation with LlamaSharp
Quite exciting this computer magic
thirty25.blog
April 16, 2025 at 8:19 PM
philco.bsky.social
Knocked out the third part of my blog series on LlamaSharp. This time on memory management.

thirty25.blog/blog/2025/04...
Thirty25 - Efficient LLM Memory Management with LlamaSharp
Quite exciting this computer magic
thirty25.blog
April 6, 2025 at 1:58 PM
philco.bsky.social
Part 2 in my "the only moral AI use is my AI use" series on LlamaSharp - Messing with the Settings of the Pipeline

thirty25.blog/blog/2025/04...
Thirty25 - Mastering LlamaSharp's Sampling Pipeline
Quite exciting this computer magic
thirty25.blog
April 4, 2025 at 1:33 PM
philco.bsky.social
As promised, time to use my blazor based blog. A quick intro into using LlamaSharp

thirty25.blog/blog/2025/04...
Thirty25 - Getting Started with LlamaSharp
Quite exciting this computer magic
thirty25.blog
April 2, 2025 at 1:48 PM
philco.bsky.social
Been over a decade since I have done any proper Windows Dev work, so I want to knock the cobwebs out relearning ReactiveUI and Avalonia. Wrapped up LlamaSharp into a little locally running chat bot.

Got it working at least - github.com/phil-scott-7...
January 19, 2025 at 1:06 AM
studiofreesia.com
LLamaSharp でGPU使えない理由わかったぁ！！！
LLamaSharp がCUDA12までしか対応していないのに、CUDA13にパス通っていてそっちを強制的に使おうとしてた…
October 12, 2025 at 8:04 AM