Fused MoE kernel
☆23Aug 10, 2026Updated 2 months ago
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:
- Code and reproducibility artifacts for reconstructing megakernel persistence with CUDA PDL☆24Aug 5, 2026Updated 2 months ago
- Reference implementation and examples of the CuTe Layout representation and algebra.☆380Sep 30, 2026Updated 3 weeks ago
- ☆18Jun 19, 2026Updated 4 months ago
- ☆51Aug 17, 2026Updated 2 months ago
- A high performance development and dispatch library for high-performance machine learning kernels.☆38Aug 15, 2026Updated 2 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.
- TensorIR is a lightweight NVIDIA-owned MLIR compiler frontend for expressing tensor computations and lowering them to NVIDIA CUDA Tile IR…☆138Oct 15, 2026Updated last week
- NaiveRT: a self-contained TP8 inference runtime for the Naive N series on eight Blackwell GPUs with UMMA support. One persistent CUDA gra…☆30Sep 27, 2026Updated 3 weeks ago
- Minimal RLM harness☆68Updated this week
- Mixture-of-experts (MoE) training megakernel for NVL72s☆625Oct 1, 2026Updated 2 weeks ago
- Speedrun for pretraining without backpropagation☆177Updated this week
- Communication patterns for AI, built on top of NCCL device and host APIs☆70Updated this week
- Public repo for kernel writing skills in CuTeDSL, Triton, Tilelang and CUDA☆25Jul 7, 2026Updated 3 months ago
- A Python DSL for Apple Metal GPU compute☆27Jul 23, 2026Updated 2 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…☆154Sep 18, 2026Updated last month
- 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.
- MoonEP: A Perfectly Balanced Expert Parallelism Library via Dynamic Redundant Experts☆1,189Oct 12, 2026Updated last week
- 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…☆54Aug 25, 2026Updated last month
- Flash-Flash KDA: H100-optimized Flash Kimi Delta Attention kernels☆24Jul 24, 2026Updated 2 months ago
- ☆130Updated this week
- mKernel: fast multi-node, multi-GPU fused kernels☆296Updated this week
- PolarGrad: A Class of Matrix-Gradient Optimizers from a Unifying Preconditioning Perspective☆18Aug 10, 2026Updated 2 months ago
- ☆11Aug 19, 2026Updated 2 months ago
- ☆24Sep 9, 2026Updated last month
- GEMMs with metal☆26Oct 5, 2026Updated 2 weeks 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.
- ☆23Updated this week
- Code for MatGPTQ: Accurate and Efficient Post-Training Matryoshka Quantization☆31Oct 6, 2026Updated 2 weeks ago
- High performance RMSNorm Implement by using SM Core Storage(Registers and Shared Memory)☆31Jan 22, 2026Updated 9 months ago
- FlashRT-HF-kernels contains standalone FlashRT CUDA/CUTLASS kernels prepared for the Hugging Face kernels community, focusing on small-ba…☆24Aug 21, 2026Updated 2 months ago
- DeepStack: Facilitating Co-Design Exploration of 3D DRAM-Stacked Accelerators for Distributed LLM Inference. Includes the MICRO 2026 AE a…☆65Oct 5, 2026Updated 2 weeks ago
- Dist-MoE implements Speed-of-Light distributed Mixture-of-Experts forward and backward kernels. They are highly optimized and fused comm-…☆17Updated this week
- ☆100Sep 8, 2026Updated last month
- ☆258Oct 14, 2026Updated last week
- Expert Specialization MoE Solution based on CUTLASS☆27Apr 14, 2026Updated 6 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.
- Claude's Tokenizer, Offline, Kinda☆85Sep 25, 2026Updated 3 weeks ago
- An open-source toolkit for BigMac-style pipeline-parallel training of multimodal large language models.☆37Jul 21, 2026Updated 3 months ago
- ☆52Jul 27, 2026Updated 2 months ago
- Curated high-performance TIRx GPU kernels☆32Updated this week
- ☆25Apr 4, 2026Updated 6 months ago
- [MLSys 26] 🥇 Solution for Gated Delta Net Track of MLSys 26 Flash infer competition☆36May 22, 2026Updated 5 months ago
- Plug-and-play PyTorch transformer research framework. Swap attention, FFN, norm, positional, connection, projection, optimizer, scheduler…☆18Updated this week