# #llm-engineering — MDRSS hashtag feed

> Public MDRSS cards tagged #llm-engineering.
> Canonical feed: https://mdrss.com/feeds/llm-engineering

## Cards (51)

### [Recsys Pipeline Architect](https://mdrss.com/llm-engineering/mlops-and-ml-systems/901385/901385.md)

A spec-and-scaffold skill for building composable recommendation, ranking, and feed pipelines. Encodes the six-stage pattern popularized by xAI's open-sourced For You algorithm (Apache 2.0) and applies it to any "top K for (user, context)" problem. Use it to give an agent explicit responsibilities, steps and constraints.

Classification: llm-engineering/mlops-and-ml-systems · Feed: llm-engineering · Updated: 2026-08-04T13:54:51.641Z · Version: 1

### [ML Pipeline Workflow](https://mdrss.com/llm-engineering/mlops-and-ml-systems/901384/901384.md)

Complete end-to-end MLOps pipeline orchestration from data preparation through model deployment. Use it to give an agent explicit responsibilities, steps and constraints.

Classification: llm-engineering/mlops-and-ml-systems · Feed: llm-engineering · Updated: 2026-08-04T13:54:51.641Z · Version: 1

### [Machine Learning Pipeline - Multi-Agent MLOps Orchestration](https://mdrss.com/llm-engineering/mlops-and-ml-systems/901383/901383.md)

This workflow orchestrates multiple specialized agents to build a production-ready ML pipeline following modern MLOps best practices. The approach emphasizes:. Use it to give an agent explicit responsibilities, steps and constraints.

Classification: llm-engineering/mlops-and-ml-systems · Feed: llm-engineering · Updated: 2026-08-04T13:54:51.641Z · Version: 1

### [Mlops engineer](https://mdrss.com/llm-engineering/mlops-and-ml-systems/901382/901382.md)

You are an MLOps engineer specializing in ML infrastructure, automation, and production ML systems across cloud platforms. Use it to give an agent explicit responsibilities, steps and constraints.

Classification: llm-engineering/mlops-and-ml-systems · Feed: llm-engineering · Updated: 2026-08-04T13:54:51.641Z · Version: 1

### [Ml engineer](https://mdrss.com/llm-engineering/mlops-and-ml-systems/901381/901381.md)

You are an ML engineer specializing in production machine learning systems, model serving, and ML infrastructure. Use it to give an agent explicit responsibilities, steps and constraints.

Classification: llm-engineering/mlops-and-ml-systems · Feed: llm-engineering · Updated: 2026-08-04T13:54:51.641Z · Version: 1

### [Data scientist](https://mdrss.com/llm-engineering/mlops-and-ml-systems/901380/901380.md)

You are a data scientist specializing in advanced analytics, machine learning, statistical modeling, and data-driven business insights. Use it to give an agent explicit responsibilities, steps and constraints.

Classification: llm-engineering/mlops-and-ml-systems · Feed: llm-engineering · Updated: 2026-08-04T13:54:51.641Z · Version: 1

### [VLM Collators, Dataset Format, and Pitfalls](https://mdrss.com/llm-engineering/training-and-fine-tuning/901379/901379.md)

Full detail backing the summary in SKILL.md. Base models are never named here as recommendations — the collator table below names architecture families only because the processor contract (which tensors a collator must produce) is a technical property of that family, not a mode. Use it to give an agent explicit responsibilities, steps and constraints.

Classification: llm-engineering/training-and-fine-tuning · Feed: llm-engineering · Updated: 2026-08-04T13:54:51.641Z · Version: 1

### [Vision-Language SFT](https://mdrss.com/llm-engineering/training-and-fine-tuning/901378/901378.md)

This skill assumes finetuning-method-selection already routed here: the data shape is image+text demonstrations, not preference pairs or a verifiable reward signal, and the base is a vision-language model rather than a text-only one. lora-qlora-recipes covers the text-only Lo. Use it to give an agent explicit responsibilities, steps and constraints.

Classification: llm-engineering/training-and-fine-tuning · Feed: llm-engineering · Updated: 2026-08-04T13:54:51.641Z · Version: 1

### [Conversion Recipes](https://mdrss.com/llm-engineering/training-and-fine-tuning/901377/901377.md)

Concrete JSONL-to-JSONL conversions for every pattern in SKILL.md: a graded trace to an SFT row, a pair of graded traces to a DPO pair, an expert correction to an SFT row, the rejection-sampling loop with reward-threshold selection, and the goldens-holdout check that must run b. Use it to give an agent explicit responsibilities, steps and constraints.

Classification: llm-engineering/training-and-fine-tuning · Feed: llm-engineering · Updated: 2026-08-04T13:54:51.641Z · Version: 1

### [Trace To Training Data](https://mdrss.com/llm-engineering/training-and-fine-tuning/901376/901376.md)

This skill assumes eval-harness-first already graded the traces being converted here — goldens, graders, and runs//results.json all exist before conversion starts. This is the flywheel edge that skill names in its own flow: "the same labeled traces become the training set." C. Use it to give an agent explicit responsibilities, steps and constraints.

Classification: llm-engineering/training-and-fine-tuning · Feed: llm-engineering · Updated: 2026-08-04T13:54:51.641Z · Version: 1

### [Export Commands](https://mdrss.com/llm-engineering/training-and-fine-tuning/901375/901375.md)

Complete command sequences for every format on the SKILL.md Format Map, plus the smoke-test script skeleton. CHECKPOINT DIR, MERGED DIR, GGUF DIR, and BASE MODEL are placeholders throughout — no base-model family names appear in this file. Fill each with the promoted ch. Use it to give an agent explicit responsibilities, steps and constraints.

Classification: llm-engineering/training-and-fine-tuning · Feed: llm-engineering · Updated: 2026-08-04T13:54:51.641Z · Version: 1

### [Quantized Export](https://mdrss.com/llm-engineering/training-and-fine-tuning/901374/901374.md)

The last stop after checkpoint-promotion hands off a PROMOTE verdict: a checkpoint that cleared the four-stage gate still isn't deployed until it's exported in the right format for its target runtime and proven to still work post-export. A REJECT verdict never reaches this. Use it to give an agent explicit responsibilities, steps and constraints.

Classification: llm-engineering/training-and-fine-tuning · Feed: llm-engineering · Updated: 2026-08-04T13:54:51.641Z · Version: 1

### [Preference Optimization](https://mdrss.com/llm-engineering/training-and-fine-tuning/901373/901373.md)

This skill assumes finetuning-method-selection already routed here because the data shape is preference pairs or unpaired thumbs-up/down feedback, not demonstrations (that's lora-qlora-recipes) or a verifiable reward signal (that's grpo-rlvr-training). What follows is metho. Use it to give an agent explicit responsibilities, steps and constraints.

Classification: llm-engineering/training-and-fine-tuning · Feed: llm-engineering · Updated: 2026-08-04T13:54:51.641Z · Version: 1

### [Unsloth ↔ TRL/PEFT Mapping](https://mdrss.com/llm-engineering/training-and-fine-tuning/901372/901372.md)

Unsloth is a fast-kernel wrapper over PEFT and TRL, not a replacement API — every Unsloth kwarg below has a plain TRL/PEFT equivalent. Use this table to translate an Unsloth config to plain TRL (or back), and to know which knob lives on which object in the current TRL API. Use it to give an agent explicit responsibilities, steps and constraints.

Classification: llm-engineering/training-and-fine-tuning · Feed: llm-engineering · Updated: 2026-08-04T13:54:51.641Z · Version: 1

### [LoRA/QLoRA Hyperparameter Tables](https://mdrss.com/llm-engineering/training-and-fine-tuning/901371/901371.md)

Full tables and a complete worked config backing the summary in SKILL.md. Base models are never named here — every example is labeled by size class only; see finetuning-method-selection's references/model-catalog.md for which actual model to use at a given size class. Use it to give an agent explicit responsibilities, steps and constraints.

Classification: llm-engineering/training-and-fine-tuning · Feed: llm-engineering · Updated: 2026-08-04T13:54:51.641Z · Version: 1

### [LoRA & QLoRA Recipes](https://mdrss.com/llm-engineering/training-and-fine-tuning/901370/901370.md)

This skill assumes the routing decision already happened — finetuning-method-selection should have already pointed here because the data shape is demonstrations (SFT), not preference pairs or a verifiable reward signal. What follows is the current best-practice recipe for confi. Use it to give an agent explicit responsibilities, steps and constraints.

Classification: llm-engineering/training-and-fine-tuning · Feed: llm-engineering · Updated: 2026-08-04T13:54:51.641Z · Version: 1

### [GRPO Reward Function Library](https://mdrss.com/llm-engineering/training-and-fine-tuning/901369/901369.md)

Complete, runnable reward functions for TRL's GRPOTrainer. Every function here follows the current TRL reward-function signature: it accepts completions plus any extra dataset columns as keyword arguments, and returns a list float  the same length as completions. Base mod. Use it to give an agent explicit responsibilities, steps and constraints.

Classification: llm-engineering/training-and-fine-tuning · Feed: llm-engineering · Updated: 2026-08-04T13:54:51.641Z · Version: 1

### [GRPO & RLVR Training](https://mdrss.com/llm-engineering/training-and-fine-tuning/901368/901368.md)

This skill assumes finetuning-method-selection already routed here because the target behavior has a verifiable pass/fail signal — not demonstrations (lora-qlora-recipes) or preference pairs (preference-optimization). What follows is when RL is the right tool, the reference. Use it to give an agent explicit responsibilities, steps and constraints.

Classification: llm-engineering/training-and-fine-tuning · Feed: llm-engineering · Updated: 2026-08-04T13:54:51.641Z · Version: 1

### [Memory Math](https://mdrss.com/llm-engineering/training-and-fine-tuning/901367/901367.md)

Last verified: 2026-07-13 — refresh when a new size-class anchor is validated or optimizer/dtype defaults change. Use it to give an agent explicit responsibilities, steps and constraints.

Classification: llm-engineering/training-and-fine-tuning · Feed: llm-engineering · Updated: 2026-08-04T13:54:51.641Z · Version: 1

### [Fine-Tuning Method Selection](https://mdrss.com/llm-engineering/training-and-fine-tuning/901366/901366.md)

This is the router skill for the fine-tuning lifecycle: it decides whether fine-tuning is the right tool at all, and if so, which method and which base-model size class. Every other skill in this plugin assumes this routing already happened — start here before opening lora-qlora. Use it to give an agent explicit responsibilities, steps and constraints.

Classification: llm-engineering/training-and-fine-tuning · Feed: llm-engineering · Updated: 2026-08-04T13:54:51.641Z · Version: 1

### [Judge Calibration Protocol](https://mdrss.com/llm-engineering/training-and-fine-tuning/901365/901365.md)

The full procedure behind SKILL.md's "Judge Calibration Is a Prerequisite" section. Any grader routed to an LLM-judge follows this before its verdicts count toward a pass rate or a checkpoint promotion decision. Use it to give an agent explicit responsibilities, steps and constraints.

Classification: llm-engineering/training-and-fine-tuning · Feed: llm-engineering · Updated: 2026-08-04T13:54:51.641Z · Version: 1

### [Grader Templates](https://mdrss.com/llm-engineering/training-and-fine-tuning/901364/901364.md)

Runnable examples for the four grader shapes named in SKILL.md's Graders section: schema-compliance, exact-match with normalization, execution-based, and LLM-judge. Every grader returns a binary pass/fail — never a Likert score — per the plugin-wide rule. Wire each one to exact. Use it to give an agent explicit responsibilities, steps and constraints.

Classification: llm-engineering/training-and-fine-tuning · Feed: llm-engineering · Updated: 2026-08-04T13:54:51.641Z · Version: 1

### [Eval Harness First](https://mdrss.com/llm-engineering/training-and-fine-tuning/901363/901363.md)

The Phase 0 gate for the whole plugin: finetuning-method-selection and every downstream skill assume this harness exists before a training config gets written. The harness is not a run-end side artifact — it is the data-curation engine. The same labeled traces that build the go. Use it to give an agent explicit responsibilities, steps and constraints.

Classification: llm-engineering/training-and-fine-tuning · Feed: llm-engineering · Updated: 2026-08-04T13:54:51.641Z · Version: 1

### [Synthetic Data: Generation, Filtering, Distillation](https://mdrss.com/llm-engineering/training-and-fine-tuning/901362/901362.md)

Full detail backing SKILL.md's Synthetic Data Rules section: the generation-method ranking, the filter funnel candidate generations pass through before joining the training set, and the teacher→student distillation pattern. Base models are never named as recommendations here. Use it to give an agent explicit responsibilities, steps and constraints.

Classification: llm-engineering/training-and-fine-tuning · Feed: llm-engineering · Updated: 2026-08-04T13:54:51.641Z · Version: 1

### [Dataset Formats and Template Application](https://mdrss.com/llm-engineering/training-and-fine-tuning/901361/901361.md)

Concrete JSONL examples for every format in SKILL.md's Format Selection table, a template-application code sketch using current TRL conventions, and the ShareGPT→role/content conversion note. Base models are never named here — every code example uses a BASE MODEL placeholder;. Use it to give an agent explicit responsibilities, steps and constraints.

Classification: llm-engineering/training-and-fine-tuning · Feed: llm-engineering · Updated: 2026-08-04T13:54:51.641Z · Version: 1

### [Dataset Curation](https://mdrss.com/llm-engineering/training-and-fine-tuning/901360/901360.md)

This skill assumes finetuning-method-selection already routed here — the next step is preparing data, not choosing a method. What follows: format selection by target method, the template/packing mechanics behind the most common silent training failures, rules for mixing in synt. Use it to give an agent explicit responsibilities, steps and constraints.

Classification: llm-engineering/training-and-fine-tuning · Feed: llm-engineering · Updated: 2026-08-04T13:54:51.641Z · Version: 1

### [Gate Templates](https://mdrss.com/llm-engineering/training-and-fine-tuning/901359/901359.md)

Complete promotion-report.md template, the drift-suite scoring table, the paired-arena protocol, and a replay-mix configuration example referenced from SKILL.md. BASE MODEL and CHECKPOINT are placeholders throughout — no base model family names appear in this file. Benchm. Use it to give an agent explicit responsibilities, steps and constraints.

Classification: llm-engineering/training-and-fine-tuning · Feed: llm-engineering · Updated: 2026-08-04T13:54:51.641Z · Version: 1

### [Checkpoint Promotion](https://mdrss.com/llm-engineering/training-and-fine-tuning/901358/901358.md)

The Phase 5 gate for the whole plugin: a checkpoint that trains cleanly and beats its task metric still doesn't ship without clearing all four stages below. eval-harness-first built the suite re-run here — this skill is where that suite's baseline decides something. Use it to give an agent explicit responsibilities, steps and constraints.

Classification: llm-engineering/training-and-fine-tuning · Feed: llm-engineering · Updated: 2026-08-04T13:54:51.641Z · Version: 1

### [Fine-tune for: $ARGUMENTS](https://mdrss.com/llm-engineering/training-and-fine-tuning/901357/901357.md)

This command orchestrates the eval-gated fine-tuning lifecycle across seven phases, each owned by a specialist agent and gated by the artifact the prior phase produced:. Use it to give an agent explicit responsibilities, steps and constraints.

Classification: llm-engineering/training-and-fine-tuning · Feed: llm-engineering · Updated: 2026-08-04T13:54:51.641Z · Version: 1

### [Llm finetuning training engineer](https://mdrss.com/llm-engineering/training-and-fine-tuning/901356/901356.md)

You are the fine-tuning training engineer: the workhorse who takes a training-brief.md someone else already justified and turns it into a dataset, a running job, and an exported artifact. You don't re- litigate method or model choice, and you don't decide whether a checkpoint s. Use it to give an agent explicit responsibilities, steps and constraints.

Classification: llm-engineering/training-and-fine-tuning · Feed: llm-engineering · Updated: 2026-08-04T13:54:51.641Z · Version: 1

### [Llm finetuning eval engineer](https://mdrss.com/llm-engineering/training-and-fine-tuning/901355/901355.md)

You are the fine-tuning eval engineer: the independent gatekeeper who builds the measuring stick before anyone trains against it, and reads that same measuring stick to decide whether a trained checkpoint ships. You own the two phases that bound the lifecycle — Phase 0 before a t. Use it to give an agent explicit responsibilities, steps and constraints.

Classification: llm-engineering/training-and-fine-tuning · Feed: llm-engineering · Updated: 2026-08-04T13:54:51.641Z · Version: 1

### [Llm finetuning architect](https://mdrss.com/llm-engineering/training-and-fine-tuning/901354/901354.md)

You are the fine-tuning architect: a skeptical strategist who decides whether fine-tuning is the right tool at all before anyone opens a training config. You are the gate-keeper standing between "the user wants to fine-tune" and the first line of a training script — most requests. Use it to give an agent explicit responsibilities, steps and constraints.

Classification: llm-engineering/training-and-fine-tuning · Feed: llm-engineering · Updated: 2026-08-04T13:54:51.641Z · Version: 1

### [G1: CUDA 12/13 ABI Mismatch](https://mdrss.com/llm-engineering/inference-and-quantization/901285/901285.md)

Last verified: 2026-07-14 — refresh when CUDA, PyTorch, or the DGX Spark stack ships a new major version. Use it to give an agent explicit responsibilities, steps and constraints.

Classification: llm-engineering/inference-and-quantization · Feed: llm-engineering · Updated: 2026-08-04T13:54:51.641Z · Version: 1

### [Spark Training Gotchas](https://mdrss.com/llm-engineering/inference-and-quantization/901284/901284.md)

DGX Spark's GB10 chip (Grace Blackwell, SM121, 128GB unified memory, aarch64) has ten recurring failure modes across launch, memory, thermals, bandwidth, and precision. Each is named G1–G10 so it can be checked by number — the numbering is load-bearing for tooling that runs these. Use it to give an agent explicit responsibilities, steps and constraints.

Classification: llm-engineering/inference-and-quantization · Feed: llm-engineering · Updated: 2026-08-04T13:54:51.641Z · Version: 1

### [Spark Environment Setup](https://mdrss.com/llm-engineering/inference-and-quantization/901281/901281.md)

DGX Spark ships a GB10 Grace Blackwell chip: aarch64 CPU, SM121 GPU, 128GB unified memory, CUDA 13. This is a narrower and younger platform than a standard x86 CUDA 12 box, so package selection and ABI matching matter more than usual — the wheel ecosystem for aarch64 + CUDA 13 is. Use it to give an agent explicit responsibilities, steps and constraints.

Classification: llm-engineering/inference-and-quantization · Feed: llm-engineering · Updated: 2026-08-04T13:54:51.641Z · Version: 1

### [Pull Request Enhancement](https://mdrss.com/llm-engineering/rag-and-knowledge-systems/901240/901240.md)

You are a PR optimization expert specializing in creating high-quality pull requests that facilitate efficient code reviews. Generate comprehensive PR descriptions, automate review processes, and ensure PRs follow best practices for clarity, size, and reviewability. Use it to give an agent explicit responsibilities, steps and constraints.

Classification: llm-engineering/rag-and-knowledge-systems · Feed: llm-engineering · Updated: 2026-08-04T13:54:51.641Z · Version: 1

### [LLM (Large Language Models) FineTuning Projects and notes on common practical techniques](https://mdrss.com/llm-engineering/training-and-fine-tuning/901107/901107.md)

logo : https://github.com/rohan-paul/rohan-paul/blob/master/assets/png. Use it when a task needs concrete terminology, constraints or implementation detail.

Classification: llm-engineering/training-and-fine-tuning · Feed: llm-engineering · Updated: 2026-08-04T13:54:51.641Z · Version: 1

### [PremSQL | Easy to use fully local RAG on Databases](https://mdrss.com/llm-engineering/rag-and-knowledge-systems/901104/901104.md)

PremSQL is an open-source library designed to help developers create secure, fully local Text-to-SQL solutions using small language models. It provides all the essential tools to build and deploy end-to-end Text-to-SQL pipelines with customizable components, making it ideal for s. Use it to build a structured path from fundamentals to hands-on practice.

Classification: llm-engineering/rag-and-knowledge-systems · Feed: llm-engineering · Updated: 2026-08-04T13:54:51.641Z · Version: 1

### [pgvector](https://mdrss.com/llm-engineering/rag-and-knowledge-systems/901103/901103.md)

Plus ACID compliance, point-in-time recovery, JOINs, and all of the other great features of Postgres. Use it to make implementation decisions and avoid common dead ends.

Classification: llm-engineering/rag-and-knowledge-systems · Feed: llm-engineering · Updated: 2026-08-04T13:54:51.641Z · Version: 1

### [What is a good dataset?](https://mdrss.com/llm-engineering/training-and-fine-tuning/901097/901097.md)

A curated reference on training & fine-tuning centered on What is a good dataset?. Use it when a task needs concrete terminology, constraints or implementation detail.

Classification: llm-engineering/training-and-fine-tuning · Feed: llm-engineering · Updated: 2026-08-04T13:54:51.641Z · Version: 1

### [MarkItDown](https://mdrss.com/llm-engineering/rag-and-knowledge-systems/901092/901092.md)

MarkItDown is a lightweight Python utility for converting various files to Markdown for use with LLMs and related text analysis pipelines. To this end, it is most comparable to textract, but with a focus on preserving important document structure and content as Markdown (includin. Use it to build a structured path from fundamentals to hands-on practice.

Classification: llm-engineering/rag-and-knowledge-systems · Feed: llm-engineering · Updated: 2026-08-04T13:54:51.641Z · Version: 1

### [Synthetic Data Kit](https://mdrss.com/llm-engineering/training-and-fine-tuning/901088/901088.md)

Tool for generating high-quality synthetic datasets to fine-tune LLMs. Use it to navigate the topic and choose relevant methods, papers or tools.

Classification: llm-engineering/training-and-fine-tuning · Feed: llm-engineering · Updated: 2026-08-04T13:54:51.641Z · Version: 1

### [Transfer Engine (TE)](https://mdrss.com/llm-engineering/inference-and-quantization/901084/901084.md)

Mooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI. Under real workloads, Mooncake’s innovative architecture enables Kimi to handle 75% more requests while adhering to SLOs. Use it to ground design choices in named patterns, trade-offs and examples.

Classification: llm-engineering/inference-and-quantization · Feed: llm-engineering · Updated: 2026-08-04T13:54:51.641Z · Version: 1

### [LLMTools: Run & Finetune LLMs on Consumer GPUs](https://mdrss.com/llm-engineering/inference-and-quantization/901083/901083.md)

LLMTools is a user-friendly library for running and finetuning LLMs in low-resource settings. Features include: 🔨 LLM finetuning in 2-bit, 3-bit, 4-bit precision using the ModuLoRA algorithm 🐍 Easy-to-use Python API for quantization, inference, and finetuning 🤖 Modular supp. Use it to navigate the topic and choose relevant methods, papers or tools.

Classification: llm-engineering/inference-and-quantization · Feed: llm-engineering · Updated: 2026-08-04T13:54:51.641Z · Version: 1

### [TRL - Transformers Reinforcement Learning](https://mdrss.com/llm-engineering/inference-and-quantization/901071/901071.md)

TRL is a cutting-edge library designed for post-training foundation models using advanced techniques like Supervised Fine-Tuning (SFT), Group Relative Policy Optimization (GRPO), and Direct Preference Optimization (DPO). Built on top of the 🤗 Transformers ecosystem, TRL supports. Use it to navigate the topic and choose relevant methods, papers or tools.

Classification: llm-engineering/inference-and-quantization · Feed: llm-engineering · Updated: 2026-08-04T13:54:51.641Z · Version: 1

### [StageRAG: A Framework for Building Hallucination-Resistant RAG Applications](https://mdrss.com/llm-engineering/rag-and-knowledge-systems/901061/901061.md)

StageRAG is a lightweight, production-ready RAG framework designed to give you precise control over the speed-versus-accuracy trade-off. It allows you to build high-factuality applications while gracefully managing uncertainty in LLM responses. Use it to navigate the topic and choose relevant methods, papers or tools.

Classification: llm-engineering/rag-and-knowledge-systems · Feed: llm-engineering · Updated: 2026-08-04T13:54:51.641Z · Version: 1

### [Python Bindings for llama.cpp](https://mdrss.com/llm-engineering/inference-and-quantization/901042/901042.md)

Simple Python bindings for @ggerganov's llama.cpp library. This package provides:. Use it to ground design choices in named patterns, trade-offs and examples.

Classification: llm-engineering/inference-and-quantization · Feed: llm-engineering · Updated: 2026-08-04T13:54:51.641Z · Version: 1

### [AQLM](https://mdrss.com/llm-engineering/inference-and-quantization/901037/901037.md)

Official PyTorch implementation for Extreme Compression of Large Language Models via Additive Quantization. Use it to navigate the topic and choose relevant methods, papers or tools.

Classification: llm-engineering/inference-and-quantization · Feed: llm-engineering · Updated: 2026-08-04T13:54:51.641Z · Version: 1

### [SAM3-LoRA: Efficient Fine-Tuning with Low-Rank Adaptation](https://mdrss.com/llm-engineering/training-and-fine-tuning/901032/901032.md)

Quick Start • Architecture • Training • Validation • Inference • Examples • Configuration • Troubleshooting. Use it to ground design choices in named patterns, trade-offs and examples.

Classification: llm-engineering/training-and-fine-tuning · Feed: llm-engineering · Updated: 2026-08-04T13:54:51.641Z · Version: 1

### [Advanced RAG Techniques 🚀](https://mdrss.com/llm-engineering/rag-and-knowledge-systems/901025/901025.md)

A community-driven hub of 42+ runnable notebooks covering RAG techniques from foundational to cutting-edge - the intuition, the code, and the references to build more accurate, context-rich retrieval systems. Use it as a repeatable review, validation or hardening pass.

Classification: llm-engineering/rag-and-knowledge-systems · Feed: llm-engineering · Updated: 2026-08-04T13:54:51.641Z · Version: 1

### [Awesome Model Quantization](https://mdrss.com/llm-engineering/inference-and-quantization/901001/901001.md)

This repo collects papers, documents, and codes about model quantization for anyone who wants to research it. We are continuously improving the project. Use it to navigate the topic and choose relevant methods, papers or tools.

Classification: llm-engineering/inference-and-quantization · Feed: llm-engineering · Updated: 2026-08-04T13:54:51.641Z · Version: 1