# \#llm

**URL:** https://discourse.julialang.org/tag/llm/1389.md

[Latest](https://discourse.julialang.org/latest.md) · [Categories](https://discourse.julialang.org/categories.md) · [Tags](https://discourse.julialang.org/tags.md)

---

## [Are there any official SKILLs related to Julia development from the Julia community?](https://discourse.julialang.org/t/are-there-any-official-skills-related-to-julia-development-from-the-julia-community/138760)

<div class="topic-metadata">

**Author:** [@WuSiren](https://discourse.julialang.org/u/WuSiren)\
**Replies:** 2\
**Last updated:** [August 19, 2026, 10:20pm UTC](https://discourse.julialang.org/t/are-there-any-official-skills-related-to-julia-development-from-the-julia-community/138760 "2026-08-19T22:20:23Z")

</div>

Are there any official SKILLs related to Julia development from the Julia community?

---

## [Proposal: LLMs and Generative AI](https://discourse.julialang.org/t/proposal-llms-and-generative-ai/138463)

<div class="topic-metadata">

**Author:** [@mantzaris](https://discourse.julialang.org/u/mantzaris)\
**Replies:** 0\
**Last updated:** [July 24, 2026, 9:26pm UTC](https://discourse.julialang.org/t/proposal-llms-and-generative-ai/138463 "2026-07-24T21:26:31Z")

</div>

Julia for LLMs and Generative AI I wanted to see what the community thinks about creating a dedicated LLMs and Generative AI section under the Domains category. Working on: Training foundation models Fine tuning and a…

---

## [\[ANN\]: Three small single-provider LLM API clients: AnthropicClient.jl, GroqClient.jl, GoogleLLMClient.jl](https://discourse.julialang.org/t/ann-three-small-single-provider-llm-api-clients-anthropicclient-jl-groqclient-jl-googlellmclient-jl/137632)

<div class="topic-metadata">

**Author:** [@yoninazarathy](https://discourse.julialang.org/u/yoninazarathy)\
**Replies:** 0\
**Last updated:** [June 15, 2026, 5:12am UTC](https://discourse.julialang.org/t/ann-three-small-single-provider-llm-api-clients-anthropicclient-jl-groqclient-jl-googlellmclient-jl/137632 "2026-06-15T05:12:37Z")

</div>

I’m happy to announce three small Julia packages for calling hosted LLM APIs — one each for Anthropic, Groq, and Google’s Gemini. They’re deliberately minimal and single-provider by design: thin HTTP clients sharing one…

---

## [Improving the experience of working with Julia packages with llms.txt](https://discourse.julialang.org/t/improving-the-experience-of-working-with-julia-packages-with-llms-txt/135801)

<div class="topic-metadata">

**Author:** [@csvance](https://discourse.julialang.org/u/csvance)\
**Replies:** 5\
**Last updated:** [February 24, 2026, 3:36pm UTC](https://discourse.julialang.org/t/improving-the-experience-of-working-with-julia-packages-with-llms-txt/135801 "2026-02-24T15:36:45Z")

</div>

With the 1.0.0 rewrite of gRPCClient.jl, I realized that there are not going to be any examples of using the current version of the package in LLM training data. In an effort to try and bootstrap the package for usage wi…

---

## [An LLM fine-tuned for Julia, call for comments + help](https://discourse.julialang.org/t/an-llm-fine-tuned-for-julia-call-for-comments-help/113462)

<div class="topic-metadata">

**Author:** [@cpfiffer](https://discourse.julialang.org/u/cpfiffer)\
**Replies:** 32\
**Last updated:** [February 2, 2026, 4:31pm UTC](https://discourse.julialang.org/t/an-llm-fine-tuned-for-julia-call-for-comments-help/113462 "2026-02-02T16:31:45Z")

</div>

Overview There’s been some discussion in the Julia slack about fine-tuning a model for Julia specifically, in part because the language does not have as large an existing code base as other, much older languages. There’s…

---

## [GraphRAG for LLM-Based Code Porting](https://discourse.julialang.org/t/graphrag-for-llm-based-code-porting/134364)

<div class="topic-metadata">

**Author:** [@andreeco](https://discourse.julialang.org/u/andreeco)\
**Replies:** 0\
**Last updated:** [December 4, 2025, 10:21pm UTC](https://discourse.julialang.org/t/graphrag-for-llm-based-code-porting/134364 "2025-12-04T22:21:17Z")

</div>

In this video (from about 28:30 onwards), the speaker talks about GraphRAG for LLM-based code porting. He is from Microsoft and speaks about Rust adoption at the company. The part on GraphRAG for code porting is only ab…

---

## [Reliability of AI coding tools](https://discourse.julialang.org/t/reliability-of-ai-coding-tools/133975)

<div class="topic-metadata">

**Author:** [@Mikhail\_Kagalenko](https://discourse.julialang.org/u/Mikhail_Kagalenko)\
**Replies:** 30\
**Last updated:** [November 19, 2025, 1:16pm UTC](https://discourse.julialang.org/t/reliability-of-ai-coding-tools/133975 "2025-11-19T13:16:32Z")

</div>

It is unfortunate that this package has been developed by an “AI” tool. The code produced in this fashion is inherently unreliable.

---

## [\[Help Wanted\] Help contribute test cases to improve LLM performance on Julia code](https://discourse.julialang.org/t/help-wanted-help-contribute-test-cases-to-improve-llm-performance-on-julia-code/132991)

<div class="topic-metadata">

**Author:** [@Keno](https://discourse.julialang.org/u/Keno)\
**Replies:** 6\
**Last updated:** [November 10, 2025, 1:56pm UTC](https://discourse.julialang.org/t/help-wanted-help-contribute-test-cases-to-improve-llm-performance-on-julia-code/132991 "2025-11-10T13:56:09Z")

</div>

Hi all, For the past few weeks, I’ve been working on creating a set of benchmark test cases that will be used to evaluate and train LLMs to improve their performance on Julia code. I’m particularly interested in test ca…

---

## [Multi agent orchestration for Julia code generation: Best tooling / practices?](https://discourse.julialang.org/t/multi-agent-orchestration-for-julia-code-generation-best-tooling-practices/133488)

<div class="topic-metadata">

**Author:** [@Bill\_Holmes](https://discourse.julialang.org/u/Bill_Holmes)\
**Replies:** 1\
**Last updated:** [October 28, 2025, 8:53pm UTC](https://discourse.julialang.org/t/multi-agent-orchestration-for-julia-code-generation-best-tooling-practices/133488 "2025-10-28T20:53:39Z")

</div>

Hello all, I’m hoping to crowd source some information on best tooling and practices for multi-agent orchestration for production of Julia code. I am starting to get on the bandwagon of offloading relatively straitforwa…

---

## [\[ANN\] Introducing LLMAccess: A Simple Julia Wrapper for LLM REST APIs](https://discourse.julialang.org/t/ann-introducing-llmaccess-a-simple-julia-wrapper-for-llm-rest-apis/123664)

<div class="topic-metadata">

**Author:** [@Xing\_Shi\_Cai](https://discourse.julialang.org/u/Xing_Shi_Cai)\
**Replies:** 6\
**Last updated:** [August 29, 2025, 9:20am UTC](https://discourse.julialang.org/t/ann-introducing-llmaccess-a-simple-julia-wrapper-for-llm-rest-apis/123664 "2025-08-29T09:20:21Z")

</div>

I would like to share a little project I’ve been working on called LLMAccess. It’s a simple Julia package designed to simplify interactions with various Large Language Model (LLM) APIs by wrapping around their existing R…

---

## [Looking for custom instructions / settings for coding agents](https://discourse.julialang.org/t/looking-for-custom-instructions-settings-for-coding-agents/131471)

<div class="topic-metadata">

**Author:** [@njacki](https://discourse.julialang.org/u/njacki)\
**Replies:** 0\
**Last updated:** [August 8, 2025, 10:00am UTC](https://discourse.julialang.org/t/looking-for-custom-instructions-settings-for-coding-agents/131471 "2025-08-08T10:00:06Z")

</div>

Hi everyone, I recently did give a try to a coding agent, seeing the fuzz about it everywhere finally convinced me to click on it. I briefly tested it for scientific code translation from Fortran but already face some i…

---

## [Run the Gemma 2 9B LLM in Julia and without a GPU?](https://discourse.julialang.org/t/run-the-gemma-2-9b-llm-in-julia-and-without-a-gpu/124155)

<div class="topic-metadata">

**Author:** [@nsajko](https://discourse.julialang.org/u/nsajko)\
**Replies:** 5\
**Last updated:** [April 2, 2025, 11:01am UTC](https://discourse.julialang.org/t/run-the-gemma-2-9b-llm-in-julia-and-without-a-gpu/124155 "2025-04-02T11:01:37Z")

</div>

I’m ignorant about LLMs, machine learning, etc.; but I want to run the Gemma 2 9B large language model. I’m not interested in using it as a chat bot, rather the reason I want to use it is the fact that it defines the eva…

---

## [How to start using LLMs to help write Julia code?](https://discourse.julialang.org/t/how-to-start-using-llms-to-help-write-julia-code/120912)

<div class="topic-metadata">

**Author:** [@Nathan\_Boyer](https://discourse.julialang.org/u/Nathan_Boyer)\
**Replies:** 6\
**Last updated:** [October 5, 2024, 11:11am UTC](https://discourse.julialang.org/t/how-to-start-using-llms-to-help-write-julia-code/120912 "2024-10-05T11:11:58Z")

</div>

Continuing the discussion from Is Julia 2.0 needed?: I’m curious how people are integrating AI tools to help them code. Seems this is growing in popularity, but I’ve not really looked into how to do it myself yet. Are …

---

## [Julia is really powerful with LLMs](https://discourse.julialang.org/t/julia-is-really-powerful-with-llms/118091)

<div class="topic-metadata">

**Author:** [@Marcell\_Havlik](https://discourse.julialang.org/u/Marcell_Havlik)\
**Replies:** 0\
**Last updated:** [August 12, 2024, 12:28pm UTC](https://discourse.julialang.org/t/julia-is-really-powerful-with-llms/118091 "2024-08-12T12:28:51Z")

</div>

From the time I started to work with Sonnet 3.5. I feel like in Julia programming language the LLM is just was too skilled. I could even believe that due to the descriptive force of the julia and pythonish simplicity in…

---

## [Starting With Julia!](https://discourse.julialang.org/t/starting-with-julia/117285)

<div class="topic-metadata">

**Author:** [@ZherpiaWhiskers](https://discourse.julialang.org/u/ZherpiaWhiskers)\
**Replies:** 6\
**Last updated:** [July 21, 2024, 7:14am UTC](https://discourse.julialang.org/t/starting-with-julia/117285 "2024-07-21T07:14:28Z")

</div>

Heya! I’m a bit new to Julia, so, i’ve been studying the language for a couple of days, i already know some of the syntax, i’ve learned various types of data structures and I’m going to learn algorithms by implementing t…

---

## [📢 Julia Coders: 1-Minute Survey to Shape the Future of Gen AI](https://discourse.julialang.org/t/julia-coders-1-minute-survey-to-shape-the-future-of-gen-ai/116292)

<div class="topic-metadata">

**Author:** [@svilupp](https://discourse.julialang.org/u/svilupp)\
**Replies:** 10\
**Last updated:** [July 2, 2024, 8:34am UTC](https://discourse.julialang.org/t/julia-coders-1-minute-survey-to-shape-the-future-of-gen-ai/116292 "2024-07-02T08:34:14Z")

</div>

:fire: Julia Gen AI Survey :fire: We’ve compiled a super quick survey (5 multiple-choice questions + 2 optional open-ended ones) to understand the interest and challenges around Generative AI, Large Language Models, and…

---

## [\[ANN\] HumanEval.jl - Evaluate LLM-synthesized Julia code](https://discourse.julialang.org/t/ann-humaneval-jl-evaluate-llm-synthesized-julia-code/110433)

<div class="topic-metadata">

**Author:** [@findmyway](https://discourse.julialang.org/u/findmyway)\
**Replies:** 0\
**Last updated:** [February 20, 2024, 1:34am UTC](https://discourse.julialang.org/t/ann-humaneval-jl-evaluate-llm-synthesized-julia-code/110433 "2024-02-20T01:34:39Z")

</div>

I’m excited to announce GitHub - 01-ai/HumanEval.jl: Evaluate LLM-synthesized @JuliaLang code. . The project is the Julia version of openai/human-eval. I hope it will help Julia developers gain a better understanding of …

---

## [Julia vs C++ for Automated Reasoning](https://discourse.julialang.org/t/julia-vs-c-for-automated-reasoning/109268)

<div class="topic-metadata">

**Author:** [@Rajaram\_Venkataraman](https://discourse.julialang.org/u/Rajaram_Venkataraman)\
**Replies:** 3\
**Last updated:** [January 26, 2024, 1:21pm UTC](https://discourse.julialang.org/t/julia-vs-c-for-automated-reasoning/109268 "2024-01-26T13:21:41Z")

</div>

Hello - I have to develop an automated reasoning system that combines the power of f language models and graph processing rather than HoQ, Isabelle or LEAN type approach. It requires new development and plan to use eithe…

---

## [\[ANN\] LLMTextAnalysis.jl - Unveil Text Insights with LLMs!](https://discourse.julialang.org/t/ann-llmtextanalysis-jl-unveil-text-insights-with-llms/108705)

<div class="topic-metadata">

**Author:** [@svilupp](https://discourse.julialang.org/u/svilupp)\
**Replies:** 1\
**Last updated:** [January 17, 2024, 9:03pm UTC](https://discourse.julialang.org/t/ann-llmtextanalysis-jl-unveil-text-insights-with-llms/108705 "2024-01-17T21:03:03Z")

</div>

We’re excited to introduce LLMTextAnalysis.jl, a humble yet powerful addition to your text analysis toolkit. Not intended to compete with established tools like TextAnalysis.jl, this LLM-powered cousin complements your e…

---

## [\[ANN\] List of Awesome Generative AI in/with/for Julia Language](https://discourse.julialang.org/t/ann-list-of-awesome-generative-ai-in-with-for-julia-language/105976)

<div class="topic-metadata">

**Author:** [@svilupp](https://discourse.julialang.org/u/svilupp)\
**Replies:** 11\
**Last updated:** [December 20, 2023, 1:14pm UTC](https://discourse.julialang.org/t/ann-list-of-awesome-generative-ai-in-with-for-julia-language/105976 "2023-12-20T13:14:06Z")

</div>

Generative AI and Julia, A Perfect Combination. Don’t you think? Generative AI is moving at the speed of light and it speaks Python. In my opinion, Julia is awesome. Wouldn’t it be a shame to miss out on the GenAI revo…

---

## [Challenge: Can you beat Python and C++ in Int4 Matrix-Vector Multiply Op?](https://discourse.julialang.org/t/challenge-can-you-beat-python-and-c-in-int4-matrix-vector-multiply-op/101588)

<div class="topic-metadata">

**Author:** [@svilupp](https://discourse.julialang.org/u/svilupp)\
**Replies:** 10\
**Last updated:** [July 25, 2023, 9:44pm UTC](https://discourse.julialang.org/t/challenge-can-you-beat-python-and-c-in-int4-matrix-vector-multiply-op/101588 "2023-07-25T21:44:29Z")

</div>

TL;DR How close can we get to 4x speedup if we move from Float16 to Int4 in mat-vec multiply? Hi everyone, It’s challenge time! I’m calling on the Julia community to show Python bitsandbytes (recent release with 2-4x s…