Tiny-FSDP, a minimalistic re-implementation of the PyTorch FSDP
☆112Aug 20, 2025Updated 11 months ago
Alternatives and similar repositories for Tiny-FSDP
Users that are interested in Tiny-FSDP are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Tiny-DeepSpeed, a minimalistic re-implementation of the DeepSpeed library☆53Aug 20, 2025Updated 11 months ago
- Tiny-Megatron, a minimalistic re-implementation of the Megatron library☆32Sep 1, 2025Updated 10 months ago
- Minimal PyTorch implementation of TP, SP, FSDP and sharded-EMA☆32Nov 27, 2025Updated 7 months ago
- ☆45Oct 15, 2025Updated 9 months ago
- ZO2 (Zeroth-Order Offloading): Full Parameter Fine-Tuning 175B LLMs with 18GB GPU Memory [COLM2025]☆208Jul 16, 2025Updated last year
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- MetaAttention: A Unified and Performant Attention Framework Across Hardware Backends(PPoPP'26)☆16Dec 31, 2025Updated 6 months ago
- SC'25 UltraAttn: Efficiently Parallelizing Attention through Hierarchical Context-Tiling☆16Aug 14, 2025Updated 11 months ago
- Sample Codes using NVSHMEM on Multi-GPU☆30Jan 22, 2023Updated 3 years ago
- ☆1,298May 20, 2026Updated 2 months ago
- ☆37Aug 7, 2025Updated 11 months ago
- Code repository for the SOSP'25 paper DCP: Addressing Input Dynamism In Long-Context Training via Dynamic Context Parallelism.☆21Nov 28, 2025Updated 7 months ago
- A Triton-only attention backend for vLLM☆27Jul 14, 2026Updated last week
- ☆19May 9, 2025Updated last year
- Some funny cute/cuteDSL code snippets☆33Mar 2, 2026Updated 4 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.
- [ICML‘25] Official code for paper "Occult: Optimizing Collaborative Communication across Experts for Accelerated Parallel MoE Training an…☆13Apr 17, 2025Updated last year
- Official Repo for paper "VLCache: Computing 2% Vision Tokens and Reusing 98% for Vision-Language Inference"☆16Mar 28, 2026Updated 3 months ago
- ☆32Jul 2, 2025Updated last year
- A lightweight reinforcement learning framework that integrates seamlessly into your codebase, empowering developers to focus on algorithm…☆106Aug 25, 2025Updated 11 months ago
- ☆22May 5, 2025Updated last year
- An official implementation of FlashI2V.☆33Nov 16, 2025Updated 8 months ago
- Official code for the paper "HEXA-MoE: Efficient and Heterogeneous-Aware MoE Acceleration with Zero Computation Redundancy"☆15Mar 6, 2025Updated last year
- An efficient implementation of the NSA (Native Sparse Attention) kernel☆133Jun 24, 2025Updated last year
- Minimalistic 4D-parallelism distributed training framework for education purpose☆2,258Aug 26, 2025Updated 11 months 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.
- VeOmni: Scaling Any Modality Model Training with Model-Centric Distributed Recipe Zoo☆2,106Updated this week
- ☆20May 30, 2026Updated last month
- ☆40Dec 14, 2025Updated 7 months ago
- [MLSys 26] 🥇 Solution for Gated Delta Net Track of MLSys 26 Flash infer competition☆35May 22, 2026Updated 2 months ago
- DeepSeek-V3.2-Exp DSA Warmup Lightning Indexer training operator based on tilelang☆47Nov 19, 2025Updated 8 months ago
- ☆130Aug 10, 2025Updated 11 months ago
- Winner 🏆 (Agent-only) MLSys 2026 - FlashInfer AI Kernel Generation Contest for the DeepSeek Sparse Attention (DSA) track with an average…☆148Jun 10, 2026Updated last month
- Accelerate LLM preference tuning via prefix sharing with a single line of code☆52Jul 4, 2025Updated last year
- An extention to the GaLore paper, to perform Natural Gradient Descent in low rank subspace☆19Oct 21, 2024Updated last year
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- a size profiler for cuda binary☆71Jan 15, 2026Updated 6 months ago
- Allow torch tensor memory to be released and resumed later☆261Updated this week
- Ego4DSounds: A diverse egocentric dataset with high action-audio correspondence☆21Jun 14, 2024Updated 2 years ago
- An agent for CUDA compute-communication kernel co-design☆35May 7, 2026Updated 2 months ago
- ☆11Dec 26, 2025Updated 7 months ago
- Scaled diffusion transformer for text-to-speech synthesis (DiT + T5Gemma2 conditioning, TorchTitan & Megatron backends, tested up to 1024…☆24Mar 29, 2026Updated 3 months ago
- ☆23May 2, 2026Updated 2 months ago