A codebase for pretraining multi-billion-scale sparse GPTs.
☆27Feb 9, 2026Updated 6 months ago
Alternatives and similar repositories for Sparse-GPT-Pretraining
Users that are interested in Sparse-GPT-Pretraining are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- ☆21Jun 12, 2025Updated last year
- GPU-accelerated LLM Training Simulator☆22Jun 26, 2025Updated last year
- ☆29Jan 19, 2026Updated 6 months ago
- CODA: Rewriting Transformer Blocks as GEMM-Epilogue Programs☆238Updated this week
- ☆11Nov 20, 2024Updated last year
- Managed hosting for WordPress and PHP on Cloudways • AdManaged hosting for WordPress, Magento, Laravel, or PHP apps, on multiple cloud providers. Deploy in minutes on Cloudways by DigitalOcean.
- An experimental communicating attention kernel based on DeepEP.☆34Jul 29, 2025Updated last year
- Implementation of various evolutionary algorithms, starting with evolutionary strategies☆51May 10, 2026Updated 3 months ago
- Code for the papers: “Four Over Six: More Accurate NVFP4 Quantization with Adaptive Block Scaling” and “Adaptive Block-Scaled Data Types”☆202Apr 21, 2026Updated 3 months ago
- ☆13Nov 9, 2018Updated 7 years ago
- Simple (and currently incomplete) Python wrapper around the Opentrons HTTP API☆11Nov 26, 2025Updated 8 months ago
- Chromax is a breeding simulator based on JAX.☆10Jun 6, 2025Updated last year
- ☆25May 23, 2026Updated 2 months ago
- Implementation of Recurrent Independent Mechanisms in Pytorch☆27Apr 6, 2026Updated 4 months ago
- ☆54Jul 18, 2024Updated 2 years ago
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- Source code for our paper: "Think Fast and Slow: Step-Level Cognitive Depth Adaptation for LLM Agents".☆25Feb 20, 2026Updated 5 months ago
- ☆12Jun 5, 2024Updated 2 years ago
- ☆15Dec 26, 2025Updated 7 months ago
- ☆50Jul 14, 2026Updated 3 weeks ago
- Play YouTube videos directly in your terminal with synchronized audio using ASCII rendering or ANSI truecolor.☆17Jul 23, 2026Updated 2 weeks ago
- This module defines a type system for distributed training code, based off of JAX's sharding in types, but adapted for the PyTorch ecosys…☆35Updated this week
- A Quirky Assortment of CuTe Kernels☆1,096Updated this week
- Fused KL divergence from hidden states for knowledge distillation☆21Apr 28, 2026Updated 3 months ago
- Distributed MoE in a Single Kernel [NeurIPS '25]☆281May 5, 2026Updated 3 months ago
- Deploy open-source AI quickly and easily - Special Bonus Offer • AdRunpod Hub is built for open source. One-click deployment and autoscaling endpoints without provisioning your own infrastructure.
- Gumbel-Softmax post-training quantization for LLMs (1–3 bit scalar, INT/GGUF-compatible).☆18Jul 11, 2026Updated 3 weeks ago
- ☆10Oct 28, 2024Updated last year
- Quora Paraphrasing Dataset Bahasa Indonesia Version☆11Apr 18, 2021Updated 5 years ago
- ☆11Oct 21, 2023Updated 2 years ago
- Train a SmolLM-style llm on fineweb-edu in JAX/Flax with an assortment of optimizers.☆19Jul 24, 2025Updated last year
- Build contrasts for models defined with formulaic☆13Updated this week
- ☆73Jun 3, 2026Updated 2 months ago
- turboquant-based compression engine for LLM KV cache☆62Apr 3, 2026Updated 4 months ago
- ☆23Jul 10, 2026Updated last month
- Managed hosting for WordPress and PHP on Cloudways • AdManaged hosting for WordPress, Magento, Laravel, or PHP apps, on multiple cloud providers. Deploy in minutes on Cloudways by DigitalOcean.
- Official PyTorch implementation for "TensorLens: End-to-End Transformer Analysis via High-Order Attention Tensors" [ACL 2026]☆48Apr 14, 2026Updated 3 months ago
- Attempt to make multiple residual streams from Bytedance's Hyper-Connections paper accessible to the public☆187May 13, 2026Updated 2 months ago
- Fault tolerance for PyTorch (HSDP, LocalSGD, DiLoCo, Streaming DiLoCo)☆530Jul 16, 2026Updated 3 weeks ago
- ☆25Apr 4, 2026Updated 4 months ago
- Muon in Int8 Precision Made Possible☆20Jun 18, 2026Updated last month
- MetaAttention: A Unified and Performant Attention Framework Across Hardware Backends(PPoPP'26)☆17Updated this week
- Open-source transpiler for CUDA Tile (13.1) migration☆19Dec 9, 2025Updated 8 months ago