Fused MoE kernel
☆24Oct 30, 2026Updated last week
Alternatives and similar repositories for prime-flash-moe
Users that are interested in prime-flash-moe are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- ☆15Jul 10, 2026Updated 4 months ago
- Flash-Flash KDA: H100-optimized Flash Kimi Delta Attention kernels☆24Jul 24, 2026Updated 3 months ago
- an rlm-style training harness☆74Updated this week
- A high performance development and dispatch library for high-performance machine learning kernels.☆38Aug 15, 2026Updated 2 months ago
- ☆51Aug 17, 2026Updated 2 months ago
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- Code and reproducibility artifacts for reconstructing megakernel persistence with CUDA PDL☆27Aug 5, 2026Updated 3 months ago
- A formally-verified compiler IR☆10May 5, 2026Updated 6 months ago
- Python package for compressing floating-point PyTorch tensors☆14Jul 22, 2024Updated 2 years ago
- PCCL (Prime Collective Communications Library) implements fault tolerant collective communications over IP☆165Sep 12, 2025Updated last year
- Reference implementation and examples of the CuTe Layout representation and algebra.☆395Nov 3, 2026Updated last week
- A Python DSL for Apple Metal GPU compute☆27Jul 23, 2026Updated 3 months ago
- Expert Specialization MoE Solution based on CUTLASS☆27Apr 14, 2026Updated 6 months ago
- An agent harness that compiles a model into one provably-correct, self-retargeting CUDA megakernel and self-tunes it past cuBLAS at batch…☆163Sep 18, 2026Updated last month
- FA4-based Relative Attention Kernel developed by TML and Colfax☆18Sep 11, 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.
- A 7B parameter model for mathematical reasoning☆45Aug 9, 2026Updated 3 months ago
- Public repo for kernel writing skills in CuTeDSL, Triton, Tilelang and CUDA☆25Jul 7, 2026Updated 4 months ago
- A framework for PyTorch to enable fault management for collective communication libraries (CCL) such as NCCL☆20Feb 9, 2026Updated 9 months ago
- Mixture-of-experts (MoE) training megakernel for NVL72s☆641Oct 1, 2026Updated last month
- [MLSys 26] 🥇 Solution for Gated Delta Net Track of MLSys 26 Flash infer competition☆38May 22, 2026Updated 5 months ago
- Communication patterns for AI, built on top of NCCL device and host APIs☆77Updated this week
- High-performance Accelerated LLM Operators☆24Updated this week
- ☆20Updated this week
- ☆28Jan 22, 2026Updated 9 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.
- Solidity contracts for the decentralized Prime Network protocol☆26Jul 6, 2025Updated last year
- mKernel: fast multi-node, multi-GPU fused kernels☆309Oct 17, 2026Updated 3 weeks ago
- ☆54Oct 22, 2026Updated 2 weeks ago
- collection with description of super-resolution related papers, repositories, datasets, loss functions and etc.☆11Dec 12, 2023Updated 2 years ago
- Compositional Muon release☆25Jun 5, 2026Updated 5 months ago
- A Multi-Policy, Multi-Agent RL Training Framework☆33Jun 16, 2026Updated 4 months ago
- ☆15Feb 23, 2025Updated last year
- PolarGrad: A Class of Matrix-Gradient Optimizers from a Unifying Preconditioning Perspective☆18Aug 10, 2026Updated 3 months ago
- ☆11May 21, 2026Updated 5 months ago
- End-to-end encrypted email - Proton Mail • AdSpecial offer: 40% Off Yearly / 80% Off First Month. All Proton services are open source and independently audited for security.
- A Pure JAX AsyncRL stack☆23Sep 7, 2026Updated 2 months ago
- https://github.com/gpu-mode/reference-kernels☆27Jul 4, 2026Updated 4 months ago
- Code for MatGPTQ: Efficient and Accurate Inference over Nested Quantized Models☆35Oct 6, 2026Updated last month
- Surgical GPU kernel benchmark: 7 hard problems, frontier coding agents, roofline-graded against hardware peak.☆19Jun 12, 2026Updated 4 months ago
- Serving DeepSeek-V4-Flash-0731-NVFP4 on 2x RTX PRO 6000 Blackwell (sm_120): vLLM patches, tuned configs, serve scripts, benchmarks☆15Aug 25, 2026Updated 2 months ago
- ☆10Aug 29, 2024Updated 2 years ago
- autonomous nanogpt optimizer speedrun☆112May 14, 2026Updated 5 months ago
Are these results useful?