A high-performance kernel library for LLM training
☆90Apr 28, 2026Updated 6 months ago
Alternatives and similar repositories for linghe
Users that are interested in linghe are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- ☆15Feb 26, 2026Updated 8 months ago
- Ring is a reasoning MoE LLM provided and open-sourced by InclusionAI, derived from Ling.☆108Aug 5, 2025Updated last year
- CUDA kernels for linear attention variants, written in CuTe DSL and CUTLASS C++.☆560Updated this week
- Ling is a MoE LLM provided and open-sourced by InclusionAI.☆275May 14, 2025Updated last year
- ☆16Aug 26, 2026Updated 2 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.
- Ling-V2 is a MoE LLM provided and open-sourced by InclusionAI.☆283Oct 4, 2025Updated last year
- ☆20Updated this week
- FA4-based Relative Attention Kernel developed by TML and Colfax☆18Sep 11, 2026Updated 2 months ago
- ☆11Oct 29, 2026Updated last week
- 赛博苏神：你的 research 好老师☆15Jun 16, 2026Updated 4 months ago
- ☆11May 21, 2026Updated 5 months ago
- Ring-V2 is a reasoning MoE LLM provided and open-sourced by InclusionAI.☆99Oct 23, 2025Updated last year
- Best practices for training DeepSeek, Mixtral, Qwen and other MoE models using Megatron Core.☆206May 29, 2026Updated 5 months ago
- Accelerating MoE with IO and Tile-aware Optimizations☆791Aug 29, 2026Updated 2 months ago
- Proton VPN Special Offer - Get 70% off • AdSpecial partner offer. Trusted by over 100 million users worldwide. Tested, Approved and Recommended by Experts.
- ☆28Feb 28, 2026Updated 8 months ago
- The Newton-Muon optimizer☆35Jun 5, 2026Updated 5 months ago
- Muon fsdp 2☆65Aug 8, 2025Updated last year
- Ulysses sequence-parallel all-to-all as a torch custom op, moved by the GPU copy engines into torch symmetric memory. Zero SM usage; 1.66…☆55Aug 25, 2026Updated 2 months ago
- Make FP4 on 5090 Great Again☆24Jul 20, 2026Updated 3 months ago
- ☆174Aug 8, 2026Updated 3 months ago
- ☆143Updated this week
- Code and reproducibility artifacts for reconstructing megakernel persistence with CUDA PDL☆27Aug 5, 2026Updated 3 months ago
- Automated CUDA kernel performance diagnostics from NVIDIA Nsight Compute (NCU) CSV exports.☆36Mar 18, 2026Updated 7 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.
- Humming is a high-performance, lightweight, and highly flexible JIT (Just-In-Time) compiled GEMM kernel library specifically designed for…☆356Updated this week
- ☆124Updated this week
- Understand your LLM before deploy☆70Updated this week
- NVSHMEM‑Tutorial: Build a DeepEP‑like GPU Buffer☆208Feb 11, 2026Updated 9 months ago
- All-in-one benchmarking platform for evaluating LLM.☆16Nov 12, 2025Updated 11 months ago
- A single-line modification to any (dualizer-based) optimizer that allows the optimizer to adapt to the scale of the gradients as they cha…☆19Jan 11, 2025Updated last year
- Accelerate inference without tears☆368Jan 23, 2026Updated 9 months ago
- A Multi-Policy, Multi-Agent RL Training Framework☆33Jun 16, 2026Updated 4 months ago
- ☆97Feb 5, 2026Updated 9 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.
- A NCCL extension library, designed to efficiently offload GPU memory allocated by the NCCL communication library.☆123Dec 17, 2025Updated 10 months ago
- ☆52Oct 9, 2026Updated last month
- Communication patterns for AI, built on top of NCCL device and host APIs☆77Updated this week
- ☆18Jun 19, 2026Updated 4 months ago
- Fast and memory-efficient exact attention☆23Updated this week
- qwen-nsa☆87Oct 14, 2025Updated last year
- ☆27Feb 27, 2026Updated 8 months ago
Are these results useful?