Analyze computation-communication overlap in V3/R1.
☆1,160Mar 21, 2025Updated last year
Alternatives and similar repositories for profile-data
Users that are interested in profile-data are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Expert Parallelism Load Balancer☆1,388Mar 24, 2025Updated last year
- A bidirectional pipeline parallelism algorithm for computation-communication overlap in DeepSeek V3/R1 training.☆2,966Jan 14, 2026Updated 5 months ago
- DeepGEMM: clean and efficient FP8 GEMM kernels with fine-grained scaling☆7,370Jun 4, 2026Updated last week
- DeepEP: an efficient expert-parallel communication library☆9,725Updated this week
- FlashMLA: Efficient Multi-head Latent Attention Kernels☆12,704Apr 30, 2026Updated last month
- Virtual machines for every use case on DigitalOcean • AdGet dependable uptime with 99.99% SLA, simple security tools, and predictable monthly pricing with DigitalOcean's virtual machines, called Droplets.
- A high-performance distributed file system designed to address the challenges of AI training and inference workloads.☆9,964May 7, 2026Updated last month
- Production-tested AI infrastructure tools for efficient AGI development and community-driven innovation☆8,003May 15, 2025Updated last year
- A lightweight data processing framework built on DuckDB and 3FS.☆4,960Mar 5, 2025Updated last year
- A fast communication-overlapping library for tensor/expert parallelism on GPUs.☆1,323Aug 28, 2025Updated 9 months ago
- Distributed Compiler based on Triton for Parallel Systems☆1,455Apr 22, 2026Updated last month
- ☆99Apr 2, 2025Updated last year
- FlashInfer: Kernel Library for LLM Serving☆5,760Updated this week
- DeepSeek-V3/R1 inference performance simulator☆196Mar 27, 2025Updated last year
- Mooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI.☆5,523Jun 6, 2026Updated last week
- GPUs on demand by Runpod - Special Offer Available • AdRun AI, ML, and HPC workloads on powerful cloud GPUs—without limits or wasted spend. Deploy GPUs in under a minute and pay by the second.
- Muon is Scalable for LLM Training☆1,492Aug 3, 2025Updated 10 months ago
- Perplexity GPU Kernels☆587Nov 7, 2025Updated 7 months ago
- A library for accelerating Transformer models on NVIDIA GPUs, including using 8-bit and 4-bit floating point (FP8 and FP4) precision on H…☆3,381Jun 6, 2026Updated last week
- NVIDIA Inference Xfer Library (NIXL)☆1,079Updated this week
- Zero Bubble Pipeline Parallelism☆458May 7, 2025Updated last year
- A throughput-oriented high-performance serving framework for LLMs☆964Mar 29, 2026Updated 2 months ago
- SGLang is a high-performance serving framework for large language models and multimodal models.☆28,886Updated this week
- Materials for learning SGLang☆841Jan 5, 2026Updated 5 months ago
- Dynamic Memory Management for Serving LLMs without PagedAttention☆487May 30, 2025Updated last year
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- A Datacenter Scale Distributed Inference Serving Framework☆7,248Updated this week
- xDiT: A Scalable Inference Engine for Diffusion Transformers (DiTs) with Massive Parallelism☆2,629Jun 4, 2026Updated last week
- CUDA Templates and Python DSLs for High-Performance Linear Algebra☆9,868Updated this week
- A lightweight design for computation-communication overlap.☆234Jan 20, 2026Updated 4 months ago
- Ring attention implementation with flash attention☆1,025Sep 10, 2025Updated 9 months ago
- Ongoing research training transformer models at scale☆16,687Updated this week
- Domain-specific language designed to streamline the development of high-performance GPU/CPU/Accelerators kernels☆6,489Updated this week
- MoBA: Mixture of Block Attention for Long-Context LLMs☆2,128Apr 3, 2025Updated last year
- DeeperGEMM: crazy optimized version☆86May 5, 2025Updated last year
- Virtual machines for every use case on DigitalOcean • AdGet dependable uptime with 99.99% SLA, simple security tools, and predictable monthly pricing with DigitalOcean's virtual machines, called Droplets.
- Efficient and easy multi-instance LLM serving☆553Mar 12, 2026Updated 3 months ago
- Disaggregated serving system for Large Language Models (LLMs).☆819Apr 6, 2025Updated last year
- ☆367Jan 28, 2026Updated 4 months ago
- Fast and memory-efficient exact attention☆24,111Updated this week
- Transformer related optimization, including BERT, GPT☆6,421Mar 27, 2024Updated 2 years ago
- TensorRT LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and supports state-of-the-art optimizat…☆13,841Updated this week
- FP16xINT4 LLM inference kernel that can achieve near-ideal ~4x speedups up to medium batchsizes of 16-32 tokens.☆1,082Sep 4, 2024Updated last year