Accelerate LLM preference tuning via prefix sharing with a single line of code
☆52Jul 4, 2025Updated 11 months ago
Alternatives and similar repositories for flash-preference
Users that are interested in flash-preference are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- ☆66Apr 26, 2025Updated last year
- ☆52May 19, 2025Updated last year
- DeeperGEMM: crazy optimized version☆86May 5, 2025Updated last year
- DeepGEMM: clean and efficient FP8 GEMM kernels with fine-grained scaling☆24Jun 3, 2026Updated last week
- DeepXTrace is a lightweight tool for precisely diagnosing slow ranks in DeepEP-based environments.☆99Jan 16, 2026Updated 4 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.
- ByteCheckpoint: An Unified Checkpointing Library for LFMs☆281Feb 2, 2026Updated 4 months ago
- A lightweight design for computation-communication overlap.☆234Jan 20, 2026Updated 4 months ago
- Flash-Muon: An Efficient Implementation of Muon Optimizer☆251Jun 15, 2025Updated 11 months ago
- Fast and memory-efficient exact attention☆21Apr 10, 2026Updated 2 months ago
- ☆45Oct 15, 2025Updated 7 months ago
- High-performance LLM operator library built on TileLang.☆130Updated this week
- An experimental communicating attention kernel based on DeepEP.☆34Jul 29, 2025Updated 10 months ago
- Multiple GEMM operators are constructed with cutlass to support LLM inference.☆20Aug 3, 2025Updated 10 months ago
- Debug print operator for cudagraph debugging☆15Aug 2, 2024Updated last year
- Deploy open-source AI quickly and easily - Special Bonus Offer • AdRunpod Hub is built for open source. One-click deployment and autoscaling endpoints without provisioning your own infrastructure.
- Composable and Embeddable Communication Runtime for Distributed AI Services☆101Updated this week
- Handwritten GEMM using Intel AMX (Advanced Matrix Extension)☆17Jan 11, 2025Updated last year
- ☆37Aug 7, 2025Updated 10 months ago
- ☆367Jan 28, 2026Updated 4 months ago
- Implement Flash Attention using Cute.☆108Dec 17, 2024Updated last year
- DeepSeek-V3.2-Exp DSA Warmup Lightning Indexer training operator based on tilelang☆44Nov 19, 2025Updated 6 months ago
- Perplexity GPU Kernels☆587Nov 7, 2025Updated 7 months ago
- ☆107May 31, 2025Updated last year
- Xmixers: A collection of SOTA efficient token/channel mixers☆28Sep 4, 2025Updated 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.
- patches for huggingface transformers to save memory☆36May 9, 2026Updated last month
- a simple API to use CUPTI☆10Aug 19, 2025Updated 9 months ago
- [Archived] For the latest updates and community contribution, please visit: https://github.com/Ascend/TransferQueue or https://gitcode.co…☆16Jan 16, 2026Updated 4 months ago
- libsmctrl论文的复现，添加了python端接口，可以在python端灵活调用接口来分配计算资源☆12May 21, 2024Updated 2 years ago
- DeepSeek-V3/R1 inference performance simulator☆196Mar 27, 2025Updated last year
- NVSHMEM‑Tutorial: Build a DeepEP‑like GPU Buffer☆192Feb 11, 2026Updated 3 months ago
- NVIDIA cuTile learn☆168Dec 9, 2025Updated 6 months ago
- ☆191May 7, 2025Updated last year
- A Distributed Attention Towards Linear Scalability for Ultra-Long Context, Heterogeneous Data Training☆840Updated this week
- 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.
- ☆32Jul 2, 2025Updated 11 months ago
- Aims to implement dual-port and multi-qp solutions in deepEP ibrc transport☆75May 9, 2025Updated last year
- ⚡️Write HGEMM from scratch using Tensor Cores with WMMA, MMA and CuTe API, Achieve Peak⚡️ Performance.☆155May 10, 2025Updated last year
- gLLM: Global Balanced Pipeline Parallelism System for Distributed LLM Serving with Token Throttling☆60Updated this week
- Best practices for training DeepSeek, Mixtral, Qwen and other MoE models using Megatron Core.☆194May 29, 2026Updated last week
- A Triton JIT runtime and ffi provider in C++☆35May 27, 2026Updated 2 weeks ago
- Unofficial description of the CUDA assembly (SASS) instruction sets.☆217Jul 18, 2025Updated 10 months ago