Minimal PyTorch implementation of TP, SP, FSDP and sharded-EMA
☆32Nov 27, 2025Updated 8 months ago
Alternatives and similar repositories for FSDP-Training
Users that are interested in FSDP-Training are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- OSP-Next☆68Jun 22, 2026Updated last month
- SC'25 UltraAttn: Efficiently Parallelizing Attention through Hierarchical Context-Tiling☆16Aug 14, 2025Updated 11 months ago
- ☆40Dec 14, 2025Updated 7 months ago
- An efficient implementation of the NSA (Native Sparse Attention) kernel☆134Jun 24, 2025Updated last year
- Code repository for the SOSP'25 paper DCP: Addressing Input Dynamism In Long-Context Training via Dynamic Context Parallelism.☆22Nov 28, 2025Updated 8 months ago
- 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.
- ☆53May 19, 2025Updated last year
- ☆46Oct 15, 2025Updated 9 months ago
- FA4-based Relative Attention Kernel developed by TML and Colfax☆18Jul 17, 2026Updated 3 weeks ago
- Tiny-FSDP, a minimalistic re-implementation of the PyTorch FSDP☆112Aug 20, 2025Updated 11 months ago
- MetaAttention: A Unified and Performant Attention Framework Across Hardware Backends(PPoPP'26)☆17Updated this week
- ☆22May 5, 2025Updated last year
- Some funny cute/cuteDSL code snippets☆33Mar 2, 2026Updated 5 months ago
- A Triton-only attention backend for vLLM☆28Jul 14, 2026Updated 3 weeks ago
- Multi-Level Triton Runner supporting Python, IR, PTX, AMDGCN, cubin and hasco.☆99May 8, 2026Updated 3 months ago
- GPUs on demand by Runpod - Special Offer Available • AdRun AI, ML, and HPC workloads on powerful cloud GPUs—without limits or wasted spend. Deploy GPUs in under a minute and pay by the second.
- [MLSys 26] 🥇 Solution for Gated Delta Net Track of MLSys 26 Flash infer competition☆36May 22, 2026Updated 2 months ago
- ☆32Jul 2, 2025Updated last year
- LLMBind: A Unified Modality-Task Integration Framework☆19Jun 16, 2024Updated 2 years ago
- NCU-driven iterative optimization workflow for CUDA/CUTLASS/Triton/CuTe DSL kernels.☆24Apr 10, 2026Updated 3 months ago
- iFSQ & LlamaGen-REPA☆104Jan 27, 2026Updated 6 months ago
- Tiny-DeepSpeed, a minimalistic re-implementation of the DeepSpeed library☆52Aug 20, 2025Updated 11 months ago
- High performance RMSNorm Implement by using SM Core Storage(Registers and Shared Memory)☆30Jan 22, 2026Updated 6 months ago
- Offical implementation of "Spike2Former: Efficient Spiking Transformer for High-performance Image Segmentation" (AAAI2025 Oral)☆43Jan 14, 2026Updated 6 months ago
- An experimental communicating attention kernel based on DeepEP.☆34Jul 29, 2025Updated last year
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- Benchmark tests supporting the TiledCUDA library.☆19Nov 19, 2024Updated last year
- a simple API to use CUPTI☆10Aug 19, 2025Updated 11 months ago
- [NSDI'26] PolyRL is a reinforcement learning framework for LLM that harvest spot instances on the cloud to reduce cost.☆19Mar 30, 2026Updated 4 months ago
- [AAAI26] Next Patch Prediction☆129Jan 2, 2025Updated last year
- ☆37Aug 7, 2025Updated last year
- [Accepted to SOSP 2026] Fast Deterministic LLM Inference☆24Jul 24, 2026Updated 2 weeks ago
- High-performance LLM operator library built on TileLang.☆168Updated this week
- TurboServe: Serving Streaming Video Generation Efficiently and Economically☆40Jul 12, 2026Updated 3 weeks ago
- [ICLR 2024] Official implementation of Spiking Graph Contrastive Learning (0️⃣1️⃣ SpikeGCL)☆33May 8, 2024Updated 2 years ago
- GPUs on demand by Runpod - Special Offer Available • AdRun AI, ML, and HPC workloads on powerful cloud GPUs—without limits or wasted spend. Deploy GPUs in under a minute and pay by the second.
- The PyTorch implementation for A Perceptual Quality Metric for Video Frame Interpolation☆45Mar 21, 2026Updated 4 months ago
- Code for the paper "AsFT: Anchoring Safety During LLM Fune-Tuning Within Narrow Safety Basin".☆37Jul 10, 2025Updated last year
- (WIP) Parallel inference for black-forest-labs' FLUX model.☆19Nov 18, 2024Updated last year
- ☆35Dec 31, 2025Updated 7 months ago
- ☆67Updated this week
- NexRL is an ultra-loosely-coupled LLM post-training framework.☆118Jul 30, 2026Updated last week
- A lightweight post-training framework for LLMs and VLMs. 51 algorithms, 38 verified models. Scales with DeepSpeed, vLLM, and Ray.☆19Updated this week