The Automated LLM Speedrunning Benchmark measures how well LLM agents can reproduce previous innovations and discover new ones in language modeling.
☆136Feb 21, 2026Updated last month
Alternatives and similar repositories for llm-speedrunner
Users that are interested in llm-speedrunner are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Code for "What really matters in matrix-whitening optimizers?"☆23Oct 31, 2025Updated 4 months ago
- UQ: Assessing Language Models on Unsolved Questions☆30Aug 26, 2025Updated 7 months ago
- Custom triton kernels for training Karpathy's nanoGPT.☆19Oct 21, 2024Updated last year
- See https://github.com/cuda-mode/triton-index/ instead!☆11May 8, 2024Updated last year
- Ongoing research training transformer language models at scale, including: BERT☆16Apr 25, 2019Updated 6 years ago
- DigitalOcean Gradient AI Platform • AdBuild production-ready AI agents using customizable tools or access multiple LLMs through a single endpoint. Create custom knowledge bases or connect external data.
- Forcing Diffuse Distributions out of Language Models☆18Sep 10, 2024Updated last year
- Code for the paper "Distinguishing the Knowable from the Unknowable with Language Models"☆11Apr 15, 2024Updated last year
- Async RL Training at Scale☆1,176Updated this week
- CLaMR: Contextualized Late-Interaction for Multimodal Content Retrieval☆24Jun 28, 2025Updated 8 months ago
- ☆26Mar 14, 2026Updated last week
- ☆24May 23, 2025Updated 10 months ago
- [NeurIPS 2025, Spotlight]: Ambient-o: Training Good models with Bad Data.☆33Jan 21, 2026Updated 2 months ago
- ☆14Apr 16, 2025Updated 11 months ago
- AIRS-Bench: an AI Research Science benchmark for quantifying the end-to-end AI research abilities of LLM agents☆67Mar 17, 2026Updated last week
- NordVPN Threat Protection Pro™ • AdTake your cybersecurity to the next level. Block phishing, malware, trackers, and ads. Lightweight app that works with all browsers.
- Learning Accurate Decision Trees with Bandit Feedback via Quantized Gradient Descent☆16Sep 8, 2022Updated 3 years ago
- A Recipe for Building LLM Reasoners to Solve Complex Instructions☆31Oct 9, 2025Updated 5 months ago
- Muon fsdp 2☆55Aug 8, 2025Updated 7 months ago
- ☆18Nov 11, 2025Updated 4 months ago
- ☆28Jan 17, 2025Updated last year
- A blog where I write about research papers and blog posts I read.☆12Nov 20, 2024Updated last year
- This repository contains expert evaluation interface and data evaluation script for the OpenScholar project.☆39Nov 19, 2024Updated last year
- Official Implementation of the paper "Jointly Reinforcing Diversity and Quality in Language Model Generations"☆57Dec 26, 2025Updated 2 months ago
- A basic pure pytorch implementation of flash attention☆16Oct 28, 2024Updated last year
- Bare Metal GPUs on DigitalOcean Gradient AI • AdPurpose-built for serious AI teams training foundational models, running large-scale inference, and pushing the boundaries of what's possible.
- [NeurIPS'25] Official codebase for "SWE-RL: Advancing LLM Reasoning via Reinforcement Learning on Open Software Evolution"☆679Mar 16, 2025Updated last year
- ☆17Aug 5, 2025Updated 7 months ago
- Simple & Scalable Pretraining for Neural Architecture Research☆309Dec 6, 2025Updated 3 months ago
- ☆21Mar 3, 2025Updated last year
- ☆48Jan 18, 2024Updated 2 years ago
- ☆23Jan 5, 2025Updated last year
- Code for NeurIPS 2024 Spotlight: "Scaling Laws and Compute-Optimal Training Beyond Fixed Training Durations"☆92Oct 30, 2024Updated last year
- The official repo for “Unleashing the Reasoning Potential of Pre-trained LLMs by Critique Fine-Tuning on One Problem” [EMNLP25]☆34Sep 1, 2025Updated 6 months ago
- Supporting code for the blog post on modular manifolds.☆120Sep 26, 2025Updated 5 months ago
- 1-Click AI Models by DigitalOcean Gradient • AdDeploy popular AI models on DigitalOcean Gradient GPU virtual machines with just a single click and start building anything your business needs.
- Triton kernels for Flux☆22Jul 7, 2025Updated 8 months ago
- CIFAR-10 speedrun: Trains to 94% accuracy in 1.98 seconds on a single NVIDIA A100 GPU.☆66Oct 17, 2025Updated 5 months ago
- A Top-Down Profiler for GPU Applications☆22Feb 29, 2024Updated 2 years ago
- [ICML 2024] Official Repository for the paper "Transformers Get Stable: An End-to-End Signal Propagation Theory for Language Models"☆10Jul 19, 2024Updated last year
- Benchmark tests supporting the TiledCUDA library.☆18Nov 19, 2024Updated last year
- MLBench Framework Core Python Library☆18Mar 1, 2023Updated 3 years ago
- Lightly-reviewed collection of community environments☆219Mar 18, 2026Updated last week