deepseek-ai / DualPipeLinks
A bidirectional pipeline parallelism algorithm for computation-communication overlap in DeepSeek V3/R1 training.
☆2,919Updated 3 weeks ago
Alternatives and similar repositories for DualPipe
Users that are interested in DualPipe are comparing it to the libraries listed below
Sorting:
- Expert Parallelism Load Balancer☆1,344Updated 10 months ago
- DeepGEMM: clean and efficient FP8 GEMM kernels with fine-grained scaling☆6,162Updated last week
- Analyze computation-communication overlap in V3/R1.☆1,141Updated 10 months ago
- DeepEP: an efficient expert-parallel communication library☆8,967Updated this week
- FlashMLA: Efficient Multi-head Latent Attention Kernels☆12,456Updated this week
- Mooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI.☆4,701Updated this week
- Production-tested AI infrastructure tools for efficient AGI development and community-driven innovation☆7,964Updated 8 months ago
- FlashInfer: Kernel Library for LLM Serving☆4,935Updated this week
- A high-performance distributed file system designed to address the challenges of AI training and inference workloads.☆9,706Updated this week
- MoBA: Mixture of Block Attention for Long-Context LLMs☆2,044Updated 10 months ago
- Domain-specific language designed to streamline the development of high-performance GPU/CPU/Accelerators kernels☆5,094Updated this week
- DeepSeekMoE: Towards Ultimate Expert Specialization in Mixture-of-Experts Language Models☆1,891Updated 2 years ago
- A lightweight data processing framework built on DuckDB and 3FS.☆4,920Updated 11 months ago
- A fast communication-overlapping library for tensor/expert parallelism on GPUs.☆1,242Updated 5 months ago
- A Datacenter Scale Distributed Inference Serving Framework☆6,052Updated this week
- Muon is Scalable for LLM Training☆1,426Updated 6 months ago
- slime is an LLM post-training framework for RL Scaling.☆3,668Updated this week
- Lightning-Fast RL for LLM Reasoning and Agents. Made Simple & Flexible.☆3,509Updated this week
- Mirage Persistent Kernel: Compiling LLMs into a MegaKernel☆2,120Updated last week
- Distributed Compiler based on Triton for Parallel Systems☆1,332Updated last week
- A compact implementation of SGLang, designed to demystify the complexities of modern LLM serving systems.☆3,297Updated 3 weeks ago
- The official repo of MiniMax-Text-01 and MiniMax-VL-01, large-language-model & vision-language-model based on Linear Attention☆3,328Updated 7 months ago
- Byted PyTorch Distributed for Hyperscale Training of LLMs and RLs☆926Updated 2 months ago
- 🐳 Efficient Triton implementations for "Native Sparse Attention: Hardware-Aligned and Natively Trainable Sparse Attention"☆964Updated this week
- A library for accelerating Transformer models on NVIDIA GPUs, including using 8-bit and 4-bit floating point (FP8 and FP4) precision on H…☆3,152Updated this week
- Transformers-compatible library for applying various compression algorithms to LLMs for optimized deployment with vLLM☆2,705Updated this week
- Simple RL training for reasoning☆3,830Updated last month
- LightLLM is a Python-based LLM (Large Language Model) inference and serving framework, notable for its lightweight design, easy scalabili…☆3,888Updated this week
- My learning notes for ML SYS.☆5,306Updated last week
- Conditional Memory via Scalable Lookup: A New Axis of Sparsity for Large Language Models☆3,630Updated 3 weeks ago