deepseek-ai / DeepGEMM
DeepGEMM: clean and efficient FP8 GEMM kernels with fine-grained scaling
☆5,064Updated last week
Alternatives and similar repositories for DeepGEMM:
Users that are interested in DeepGEMM are comparing it to the libraries listed below
- DeepEP: an efficient expert-parallel communication library☆7,289Updated last week
- A bidirectional pipeline parallelism algorithm for computation-communication overlap in V3/R1 training.☆2,656Updated 2 weeks ago
- FlashMLA: Efficient MLA decoding kernels☆11,369Updated 3 weeks ago
- Expert Parallelism Load Balancer☆1,099Updated this week
- Analyze computation-communication overlap in V3/R1.☆957Updated last week
- Production-tested AI infrastructure tools for efficient AGI development and community-driven innovation☆6,926Updated 3 weeks ago
- A high-performance distributed file system designed to address the challenges of AI training and inference workloads.☆8,269Updated last week
- Mooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI.☆2,915Updated this week
- FlashInfer: Kernel Library for LLM Serving☆2,483Updated this week
- MoBA: Mixture of Block Attention for Long-Context LLMs☆1,687Updated 3 weeks ago
- verl: Volcano Engine Reinforcement Learning for LLMs☆5,693Updated this week
- A Flexible Framework for Experiencing Cutting-edge LLM Inference Optimizations☆13,116Updated this week
- A lightweight data processing framework built on DuckDB and 3FS.☆4,386Updated 3 weeks ago
- High-performance inference framework for large language models, focusing on efficiency, flexibility, and availability.☆1,026Updated this week
- A Datacenter Scale Distributed Inference Serving Framework☆3,122Updated this week
- This is a replicate of DeepSeek-R1-Zero and DeepSeek-R1 training on small models with limited data☆3,223Updated this week
- SGLang is a fast serving framework for large language models and vision language models.☆12,427Updated this week
- DeepSeekMoE: Towards Ultimate Expert Specialization in Mixture-of-Experts Language Models☆1,609Updated last year
- Muon is Scalable for LLM Training☆974Updated last month
- My learning notes/codes for ML SYS.☆1,545Updated this week
- 📚200+ Tensor/CUDA Cores Kernels, ⚡️flash-attn-mma, ⚡️hgemm with WMMA, MMA and CuTe (98%~100% TFLOPS of cuBLAS/FA2 🎉🎉).☆2,970Updated this week
- A fast communication-overlapping library for tensor/expert parallelism on GPUs.☆811Updated last week
- The official repo of MiniMax-Text-01 and MiniMax-VL-01, large-language-model & vision-language-model based on Linear Attention☆2,415Updated last week
- Reproduce R1 Zero on Logic Puzzle☆2,208Updated last week
- Official Repo for Open-Reasoner-Zero☆1,667Updated 3 weeks ago
- s1: Simple test-time scaling☆6,051Updated 3 weeks ago
- Democratizing Reinforcement Learning for LLMs☆2,113Updated last month
- An Easy-to-use, Scalable and High-performance RLHF Framework (70B+ PPO Full Tuning & Iterative DPO & LoRA & RingAttention & RFT)☆5,919Updated this week
- Fully open data curation for reasoning models☆1,576Updated last week
- Domain-specific language designed to streamline the development of high-performance GPU/CPU/Accelerators kernels☆782Updated this week