Back to sessions

Open LLM Tech: Core Technologies

9 sessions
Days
TR212

This track focuses on the underlying core technologies and development workflows of Large Language Models (LLMs), rather than the generated output. We welcome technical submissions regarding model training, architectural optimization, and deployment practices. Topics include, but are not limited to:

  1. Model Architecture & Training Practices Explore model structural design, pre-training, and fine-tuning techniques such as LoRA or QLoRA, and methods to improve training efficiency.
  2. Quantization & Deployment Optimization Share insights on model quantization, optimization of inference engines (such as llama.cpp, vLLM), and achieving high-performance deployment across various hardware environments.
  3. Dataset Processing & Open Standards Discuss the cleaning and labeling processes for high-quality training data, and practices to ensure datasets and model weights comply with open-licensing standards.

Day 1

August 8, 2026 · TR212

TR212
9:00
10:00
11:00
12:00
13:00
14:00
15:00
16:00
17:00

Mechanistic interpretability and applications: The final fronteir of hacking

Martin Chang

Intermediate

Breaking FP64 Limits: AdaptiveGEMM Achieves Near-A100 Performance on RTX 4060 using INT8 Tensor Cores

Tsai,Ming-Han

Advanced

YAML is the New Dockerfile: Building AI Agent Systems with Docker cagent

Hrittik Roy, Parth Goswami

Intermediate

A Prompt Is Not All You Need: Building a LLM Synthetic Data Pipeline with Open-Source Tools

Nero Un 阮智軒

Intermediate

An Alternative Encoding Method: Reducing Semantic Retrieval from O(n²) to O(n)

galaxy4552

Intermediate

From RTL to Token: Walking Through the Complete LLM Inference Pipeline on an FPGA

Max

Beginner

From PyTorch to Hardware: An Introduction to LLM Compilers

Tommy Han

Advanced

From Experiments to Dashboards: Modernizing Visdom for Open AI Workflows

Mario Behling, François Cartegnie

Intermediate

Let's Quantize YOLOX from scratch with PyTorch

John Lu

Advanced