Timeline

Major Milestones

Key moments that shaped the open source LLM ecosystem.

papers

Transformer Architecture Published

Google Brain publishes 'Attention Is All You Need', introducing the Transformer — the architecture that would power all modern LLMs.

Learn more
models

GPT-2 Released

OpenAI unveils GPT-2, a 1.5B parameter language model whose surprisingly fluent text generation sparks debate over staged releases and the risks of large language models.

Learn more
papers

PyTorch Paper Published

The PyTorch team publishes 'PyTorch: An Imperative Style, High-Performance Deep Learning Library', detailing its define-by-run design. PyTorch becomes the dominant framework for LLM research and training.

Learn more
papers

Scaling Laws for Neural Language Models

OpenAI publishes 'Scaling Laws for Neural Language Models', showing that model performance improves as a predictable power law with compute, data, and parameters — the empirical foundation for the era of scaling LLMs.

Learn more
models

LLaMA Released by Meta

Meta releases LLaMA (7B-65B), proving smaller models trained on more data can compete with much larger ones. Catalyzes the open source LLM movement.

Learn more
inference

llama.cpp Launched

Georgi Gerganov releases llama.cpp, enabling LLaMA inference in C/C++ on consumer hardware including Apple Silicon. Democratizes local LLM access.

Learn more
inference

vLLM Introduces PagedAttention

UC Berkeley releases vLLM with PagedAttention, applying virtual memory concepts to KV cache. Achieves 2-4x throughput improvement and becomes the standard for LLM serving.

Learn more
models

Llama 2 Released

Meta releases Llama 2 with a permissive commercial license, including chat-tuned variants. First truly open model family that could be freely deployed in commercial products.

Learn more
models

Mistral 7B Released

Mistral AI drops Mistral 7B via a torrent link with no fanfare. Outperforms Llama 2 13B on all benchmarks, introducing sliding window attention and grouped-query attention.

Learn more
inference

SGLang Launched

The LMSYS team releases SGLang, a fast serving framework introducing RadixAttention for automatic KV cache reuse across requests. Becomes a leading high-performance inference engine alongside vLLM.

Learn more
models

Llama 3.1 405B Released

Meta releases Llama 3.1 including a 405B parameter model — the largest open-weight model at the time, competitive with GPT-4 class models on many benchmarks.

Learn more
agents

Agentic Frameworks Surge

2024 sees an explosion of agentic frameworks — LangGraph, CrewAI, AutoGen, and others mature rapidly. The focus shifts from simple chatbots to autonomous multi-step agents.

models

DeepSeek-V3 Released

DeepSeek releases V3, a 671B MoE model trained for only $5.5M — shattering cost assumptions. Introduces Multi-head Latent Attention (MLA) and matches top proprietary models.

Learn more
models

DeepSeek-R1 — Open Reasoning

DeepSeek releases R1, the first open-weight reasoning model that rivals OpenAI's o1. Achieves chain-of-thought reasoning through pure RL without supervised reasoning traces.

Learn more
models

Llama 4 Released

Meta releases Llama 4 (Scout and Maverick), its first natively multimodal, mixture-of-experts model family with very long context windows. Pushes open models further into MoE architectures.

Learn more
optimizations

DeepSeek Sparse Attention

DeepSeek introduces Sparse Attention (DSA) with DeepSeek-V3.2-Exp, selectively attending to the most relevant tokens to cut the cost of long-context inference while preserving quality.

Learn more
models

DeepSeek-V4 Released

DeepSeek releases V4-Pro and V4-Flash, trained on over 32T tokens and natively supporting a 1M-token context window. Built on Compressed Sparse Attention (CSA) and Heavily Compressed Attention (HCA) to extend context and efficiency.

Learn more
models

GLM-5.2 Released

Zhipu AI releases GLM-5.2, a large MoE model under the permissive MIT license with a 1M context window, designed for long-horizon agentic tasks. It beats GPT-5.5 on several benchmarks and trail Claude Opus 4.8 slightly, at far lower cost.

Learn more
models

Kimi K3 Released

Moonshot AI releases Kimi K3, the first open model to reach 2.8 trillion parameters. The native multimodal MoE model combines a 1M-token context window with Kimi Delta Attention and Attention Residuals.

Learn more
companies

Tech Industry Open Weight Letter

After Kimi K3 hits public download and stirs concern that policymakers may crack down on open AI systems, Jensen Huang joins Satya Nadella and dozens of tech companies on a letter warning against restricting open models.

Learn more
models

DeepSeek-V4-Flash-0731 Redraws the Cost Curve

DeepSeek retrains V4-Flash for agents and coding and ships it at the same price: $0.14 per million input tokens and $0.28 per million output tokens. Terminal Bench 2.1 jumps to 82.7 with 13B active parameters, putting an MIT-licensed model on the Pareto frontier at roughly 1% of the output price of the closed frontier.

Learn more