Skip to content

@Fulton-Engineering-Services FULTON ENGINEERING SERVICES LLC

All

    Repositories list

    31 repositories

    • vllm

      Public
      A high-throughput and memory-efficient inference and serving engine for LLMs
      Python
      •
      Apache License 2.0
      •22k•0•0•0•Updated Sep 12, 2026Sep 12, 2026

    • uccl

      Public
      UCCL is an efficient communication library for GPUs, covering collectives, P2P (e.g., KV cache transfer, RL weight transfer), and EP (e.g., GPU-driven)
      C++
      •
      Apache License 2.0
      •172•0•0•0•Updated Sep 12, 2026Sep 12, 2026

    • dgx-spark-wheels

      Public
      pip-installable PEP 503 index of prebuilt GB10 (DGX Spark / sm_121) Python wheels for flash-attn, sageattention, sageattn3, nunchaku, onnxruntime-gpu -- built i…
      cudanvidiaaarch64
      cudanvidiaaarch64python-wheelsgb10dgx-sparkpip-index
      Shell
      •
      Apache License 2.0
      •0•0•0•0•Updated Sep 9, 2026Sep 9, 2026

    • flashinfer

      Public
      FlashInfer: Kernel Library for LLM Serving
      Python
      •
      Apache License 2.0
      •1.4k•0•0•0•Updated Sep 9, 2026Sep 9, 2026

    • DeepGEMM

      Public
      DeepGEMM: clean and efficient FP8 GEMM kernels with fine-grained scaling
      Cuda
      •
      MIT License
      •1.3k•0•0•0•Updated Sep 5, 2026Sep 5, 2026

    • flextensor

      Public
      FlexTensor is a tensor offloading and management library for PyTorch that enables running large models on limited GPU memory by intelligently offloading tensors…
      Python
      •
      Apache License 2.0
      •14•0•0•0•Updated Sep 1, 2026Sep 1, 2026

    • LMCache

      Public
      LMCache: Supercharge Your LLM with the Fastest KV Cache Layer
      Python
      •
      Apache License 2.0
      •1.9k•0•0•0•Updated Aug 29, 2026Aug 29, 2026

    • nixl

      Public
      NVIDIA Inference Xfer Library (NIXL)
      C++
      •
      Other
      •440•0•0•0•Updated Aug 27, 2026Aug 27, 2026

    • Mooncake

      Public
      Mooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI.
      C++
      •
      Apache License 2.0
      •1.2k•0•0•0•Updated Aug 21, 2026Aug 21, 2026

    • causal-conv1d

      Public
      Causal depthwise conv1d in CUDA, with a PyTorch interface
      Python
      •
      BSD 3-Clause "New" or "Revised" License
      •210•0•0•0•Updated Aug 17, 2026Aug 17, 2026

    • mamba

      Public
      Mamba SSM architecture
      Python
      •
      Apache License 2.0
      •1.8k•0•0•0•Updated Aug 17, 2026Aug 17, 2026

    • py-pdf-builder

      Public
      Branded PDF report toolkit — ReportLab + matplotlib chassis with markdown, charts, Mermaid, and LaTeX math support.
      pythonpdfcharts
      pythonpdfchartslatexmatplotlibpdf-generationmermaidreportlabmarkdown-to-pdfreport-generator
      Python
      •
      Apache License 2.0
      •0•1•0•0•Updated Aug 17, 2026Aug 17, 2026

    • pytorch

      Public
      Tensors and Dynamic neural networks in Python with strong GPU acceleration
      Python
      •
      Other
      •29k•0•0•0•Updated Aug 16, 2026Aug 16, 2026

    • vision

      Public
      Datasets, Transforms and Models specific to Computer Vision
      Python
      •
      BSD 3-Clause "New" or "Revised" License
      •7.3k•0•0•0•Updated Aug 16, 2026Aug 16, 2026

    • audio

      Public
      Data manipulation and transformation for audio signal processing, powered by PyTorch
      Python
      •
      BSD 2-Clause "Simplified" License
      •796•0•0•0•Updated Aug 16, 2026Aug 16, 2026

    • triton

      Public
      Development repository for the Triton language and compiler
      MLIR
      •
      MIT License
      •3.2k•0•0•0•Updated Aug 16, 2026Aug 16, 2026

    • kilocode

      Public
      Kilo is the all-in-one agentic engineering platform. Build, ship, and iterate faster with the most popular open source coding agent.
      TypeScript
      •
      MIT License
      •3.2k•0•0•0•Updated Aug 9, 2026Aug 9, 2026

    • onnxruntime

      Public
      ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator
      C++
      •
      MIT License
      •4.2k•0•0•0•Updated Aug 5, 2026Aug 5, 2026

    • comfyui-recursive-media-picker

      Public
      Recursive subfolder listing for ComfyUI's LoadImage/LoadImageMask/LoadAudio/LoadVideo pickers, plus a fix for nested-file basename collisions in GET /view.
      media-pickercomfyuicomfyui-plugin
      media-pickercomfyuicomfyui-plugincomfyui-custom-node
      Python
      •
      MIT License
      •0•0•0•0•Updated Aug 5, 2026Aug 5, 2026

    • SageAttention

      Public
      [ICLR2025, ICML2025, NeurIPS2025 Spotlight] Quantized Attention achieves speedup of 2-5x compared to FlashAttention, without losing end-to-end metrics across la…
      Cuda
      •
      Apache License 2.0
      •506•0•0•0•Updated Jul 28, 2026Jul 28, 2026

    • nunchaku

      Public
      [ICLR2025 Spotlight] SVDQuant: Absorbing Outliers by Low-Rank Components for 4-Bit Diffusion Models
      Python
      •
      Apache License 2.0
      •277•0•0•0•Updated Jul 28, 2026Jul 28, 2026

    • flash-attention

      Public
      Fast and memory-efficient exact attention
      Python
      •
      BSD 3-Clause "New" or "Revised" License
      •3.1k•0•0•0•Updated Jul 28, 2026Jul 28, 2026

    • CodeEditSourceEditor

      Public
      A code editor view written in Swift powered by tree-sitter.
      Swift
      •
      MIT License
      •160•0•0•0•Updated Jul 6, 2026Jul 6, 2026

    • CodeEditSymbols

      Public
      Swift
      •15•0•0•0•Updated Jul 6, 2026Jul 6, 2026

    • CodeEditTextView

      Public
      A text editor specialized for displaying and editing code documents. Written in pure Swift.
      Swift
      •
      MIT License
      •54•0•0•0•Updated Jul 4, 2026Jul 4, 2026

    • CodeEditLanguages

      Public
      A Collection of Tree-Sitter Parsers for Syntax Highlighting
      Swift
      •55•0•0•0•Updated Jul 4, 2026Jul 4, 2026

    • bge-m3-embedding-server

      Public
      Axum HTTP server serving BGE-M3 dense and sparse embeddings via ONNX Runtime
      nlpdockerrust
      nlpdockerrustembeddingsonnxruntimeaxumbge-m3
      Rust
      •
      Apache License 2.0
      •1•5•0•12•Updated Jun 29, 2026Jun 29, 2026

    • bge-router

      Public
      Transparent HTTP reverse proxy for bge-m3-embedding-server: routes between GPU and CPU embedding pools based on health and queue depth
      rustgpuecs
      rustgpuecsreverse-proxyembeddingsaxumbge-m3
      Rust
      •
      Apache License 2.0
      •0•1•0•10•Updated Jun 16, 2026Jun 16, 2026

    • abb-linux-agent

      Public
      Synology Active Backup for Business Agent - Kernel 6.15+ Patches
      C
      •8•0•0•0•Updated Jun 11, 2026Jun 11, 2026

    • onnxruntime-stale-fork

      Public
      ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator
      C++
      •
      MIT License
      •4.2k•0•0•0•Updated Feb 28, 2026Feb 28, 2026
    ProTip! When viewing an organization's repositories, you can use the props. filter to filter by custom property.