NCCL communication API layer, and transport layer created from first principles.
☆16Aug 20, 2025Updated last year
Alternatives and similar repositories for NCCL-From-First-Principles
Users that are interested in NCCL-From-First-Principles are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Reference implementation of generalized orders of magnitude, as proposed in "Generalized Orders of Magnitude for Scalable, Parallel, High…☆11Dec 6, 2025Updated 11 months ago
- Tiered optimizer state allocation for memory efficient MoE training. Cuts optimizer memory by 97.4%, outperforming AdamW/Muon/Lion while …☆14Sep 10, 2026Updated 2 months ago
- GPU Performance and Cost Cheatsheet☆16Jul 13, 2025Updated last year
- ☆11Oct 29, 2026Updated 2 weeks ago
- Speed-of-Light SW efficiency by using ultra low-latency primitives for comms collectives☆13Apr 8, 2026Updated 7 months ago
- Wordpress hosting with auto-scaling - Free Trial Offer • AdFully Managed hosting for WordPress and WooCommerce businesses that need reliable, auto-scalable performance. Cloudways SafeUpdates now available.
- ☆27Feb 27, 2026Updated 8 months ago
- ☆12Nov 21, 2025Updated 11 months ago
- Triton-based Symmetric Memory operators and examples☆114May 15, 2026Updated 6 months ago
- A lightweight CuTe-based CUDA kernel for DuoAttention, optimized for large language model inference.☆12Dec 25, 2025Updated 10 months ago
- Kernels by MakoraGenerate☆15May 26, 2026Updated 5 months ago
- W4A16 MoE GEMM CUDA kernel. Tuned for H200, B200 & B300.☆14Oct 30, 2026Updated 2 weeks ago
- Mini-SGLang is a mini version of SGLang project ().☆13Sep 24, 2025Updated last year
- Reliable Sandbox for Agent, with agent-aware Checkpoint and Restore ability.☆15Aug 31, 2026Updated 2 months ago
- A survey of modern quantization formats (e.g., MXFP8, NVFP4) and inference optimization tools (e.g., TorchAO, GemLite), illustrated throu…☆12Nov 11, 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.
- GPU Functional Descriptor for memory access☆36May 24, 2026Updated 5 months ago
- DeepSeek-V3.2-Exp DSA Warmup Lightning Indexer training operator based on tilelang☆52Nov 19, 2025Updated 11 months ago
- ☆15Mar 21, 2024Updated 2 years ago
- Region-level profiling for CUDA kernels with trace, NVBit, CUPTI, NSys, and an interactive Explorer.☆135Apr 17, 2026Updated 7 months ago
- Some funny cute/cuteDSL code snippets☆35Mar 2, 2026Updated 8 months ago
- A dynamic binary instrumentation tool for tracing and analyzing GPU kernel instructions.☆85Updated this week
- ☆18Jun 19, 2026Updated 5 months ago
- Course to learn the basics of self supervised learning☆29Sep 9, 2024Updated 2 years ago
- Flash-Flash KDA: H100-optimized Flash Kimi Delta Attention kernels☆24Jul 24, 2026Updated 3 months ago
- 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.
- Python library for DeepAffects API☆10Jul 5, 2023Updated 3 years ago
- ☆19May 9, 2025Updated last year
- Agent-assisted and full-agent reproducibility package for MLSys 2026 FlashInfer AI Kernel Generation Contest submissions: kernels, agent …☆24Jul 21, 2026Updated 3 months ago
- A Triton-only attention backend for vLLM☆28Jul 14, 2026Updated 4 months ago
- Code repository for the SOSP'25 paper DCP: Addressing Input Dynamism In Long-Context Training via Dynamic Context Parallelism.☆23Nov 28, 2025Updated 11 months ago
- Code and reproducibility artifacts for reconstructing megakernel persistence with CUDA PDL☆28Aug 5, 2026Updated 3 months ago
- ☆22Nov 3, 2025Updated last year
- Make FP4 on 5090 Great Again☆25Jul 20, 2026Updated 3 months ago
- A low resolution renderer for models and images within neovim.☆30Mar 29, 2026Updated 7 months ago
- 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.
- ☆48Nov 1, 2025Updated last year
- ☆68Feb 24, 2026Updated 8 months ago
- Quickly render fractals in CUDA☆64Jul 26, 2025Updated last year
- A Low-Overhead tool for Floating-Point Exception Detection in NVIDIA GPUs☆16Dec 17, 2024Updated last year
- associative floating point addition☆21Apr 30, 2024Updated 2 years ago
- ☆28Oct 1, 2025Updated last year
- Flash Attention 2 CUDA implementations☆14Apr 29, 2025Updated last year
Are these results useful?