Archive

2026  3

June  1

How to Choose the Right Agent Architecture?

Created: 2026-06-21 · Updated: 2026-06-21 · 21 min · 4450 words · Yue Shui

May  1

GPU Kernel Generation and Optimization with Coding Agents: MLSys 2026 FlashInfer Contest Summary

Created: 2026-05-18 · Updated: 2026-05-25 · 10 min · 2047 words · Yue Shui

February  1

Self-Evolving Agents

Created: 2026-02-20 · Updated: 2026-03-16 · 14 min · 2785 words · Yue Shui

2025  17

December  1

DeepSeek-V3.2 Series

Created: 2025-12-31 · Updated: 2025-12-31 · 14 min · 2921 words · Yue Shui

November  1

Scaling Laws

Created: 2025-11-19 · Updated: 2026-06-22 · 14 min · 2789 words · Yue Shui

September  1

Agentic RL

Created: 2025-09-30 · Updated: 2025-09-30 · 24 min · 5071 words · Yue Shui

August  1

gpt-oss & GPT-5

Created: 2025-08-24 · Updated: 2025-08-24 · 12 min · 2545 words · Yue Shui

June  1

Large Language Model Inference

Created: 2025-06-29 · Updated: 2025-06-29 · 43 min · 9021 words · Yue Shui

May  2

vLLM: High-Throughput, Memory-Efficient LLM Serving

Created: 2025-05-17 · Updated: 2025-05-17 · 20 min · 4250 words · Yue Shui

Multimodal Large Language Models

Created: 2025-05-04 · Updated: 2025-05-04 · 48 min · 10215 words · Yue Shui

April  2

DeepSeek-V2 vs V3

Created: 2025-04-18 · Updated: 2025-04-18 · 63 min · 13253 words · Yue Shui

The LLaMA Herd

Created: 2025-04-06 · Updated: 2025-04-06 · 33 min · 6861 words · Yue Shui

March  2

Large Language Model Agents

Created: 2025-03-27 · Updated: 2025-09-02 · 38 min · 7929 words · Yue Shui

Parallelism and Memory Optimization Techniques for Training Large Models

Created: 2025-03-01 · Updated: 2025-03-01 · 60 min · 12764 words · Yue Shui

February  2

LLM Alignment: DPO

Created: 2025-02-08 · Updated: 2025-02-08 · 13 min · 2578 words · Yue Shui

Normalization in Deep Learning

Created: 2025-02-01 · Updated: 2025-02-01 · 13 min · 2583 words · Yue Shui

January  4

Deep Reinforcement Learning (Ongoing Updates)

Created: 2025-01-31 · Updated: 2025-01-31 · 34 min · 7230 words · Yue Shui

OpenAI o1 Replication Progress: DeepSeek-R1

Created: 2025-01-27 · Updated: 2025-01-27 · 48 min · 10183 words · Yue Shui

Attention Mechanisms in Transformers: Comparing MHA, MQA, and GQA

Created: 2025-01-16 · Updated: 2025-01-16 · 29 min · 6173 words · Yue Shui

Building Domain-Specific LLMs

Created: 2025-01-05 · Updated: 2025-01-05 · 21 min · 4394 words · Yue Shui

2024  1

December  1

Building a Home Deep Learning Rig with Dual RTX 4090 GPUs

Created: 2024-12-21 · Updated: 2024-12-21 · 10 min · 1989 words · Yue Shui

2021  1

April  1

Stock Price Prediction and Quantitative Strategy Based on Deep Learning

Created: 2021-04-21 · Updated: 2021-04-21 · 65 min · 13717 words · Yue Shui