Lynn 原生 LLM 推理引擎 · W4A8/NVFP4 量化 · 自写 CUDA/Triton kernel · MoE · 投机解码 | Lynn-native LLM inference engine for NVIDIA Blackwell
☆28Jun 8, 2026Updated 5 months ago
Alternatives and similar repositories for lynn-engine
Users that are interested in lynn-engine are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- ☆14Jun 26, 2022Updated 4 years ago
- ☆27Jun 16, 2026Updated 4 months ago
- Official PyTorch implementation of WPS from our paper: WPS-SAM: Towards Weakly-Supervised Part Segmentation with Foundation Models☆14Jun 12, 2025Updated last year
- Record interesting and meaningful papers and repositories seen daily.☆18Updated this week
- Qwen3.8-27B on one RTX 4090: full native 262K context via E8 4-bit KV, up to 149 tok/s code decode with MTP3, sm_89-retuned attention pre…☆15Sep 29, 2026Updated last month
- Bare Metal GPUs on DigitalOcean Gradient AI • AdPurpose-built for serious AI teams training foundational models, running large-scale inference, and pushing the boundaries of what's possible.
- [IEEE RA-L&ICRA2025] Think Step by Step: Chain-of-Gesture Prompting for Error Detection in Robotic Surgical Videos☆15Aug 26, 2025Updated last year
- ☆10Mar 10, 2019Updated 7 years ago
- SDNQ support for ComfyUI☆20Jan 6, 2026Updated 10 months ago
- SGLang 学习手册 — 9 部分中文工程笔记，对照源码逐章讲解☆40Aug 28, 2026Updated 2 months ago
- fused MoE kernel in Candle backend☆14Feb 3, 2026Updated 9 months ago
- mybatis-audit-tool☆11Nov 16, 2022Updated 3 years ago
- A survey of modern quantization formats (e.g., MXFP8, NVFP4) and inference optimization tools (e.g., TorchAO, GemLite), illustrated throu…☆12Nov 11, 2025Updated last year
- Running LLaMA 3 with Rust.☆10May 21, 2024Updated 2 years ago
- 更纯粹、更高压缩率的Tokenizer in Rust☆14Sep 7, 2026Updated 2 months ago
- Bare Metal GPUs on DigitalOcean Gradient AI • AdPurpose-built for serious AI teams training foundational models, running large-scale inference, and pushing the boundaries of what's possible.
- Common template for pytorch project. Easy to extent and modify for new project.☆12Dec 13, 2022Updated 3 years ago
- ☆17Nov 19, 2020Updated 5 years ago
- Graph model execution API for Candle☆19Jul 27, 2025Updated last year
- 基于 C++23 的模块化 LLM 推理框架，原生解析 GGUF 格式。☆52Jun 19, 2026Updated 4 months ago
- ☆17Nov 28, 2024Updated last year
- ☆20Oct 5, 2025Updated last year
- A source-to-source compiler for optimizing CUDA dynamic parallelism by aggregating launches☆15Jun 21, 2019Updated 7 years ago
- Multi-tenant streaming ASR server for Qwen3-ASR (vLLM AsyncLLMEngine). Drop-in replacement for qwen-asr-demo-streaming.☆14Nov 3, 2026Updated last week
- ☆11Jan 14, 2026Updated 10 months ago
- AI Agents on DigitalOcean Gradient AI Platform • AdBuild production-ready AI agents using customizable tools or access multiple LLMs through a single endpoint. Create custom knowledge bases or connect external data.
- ☆14Mar 1, 2020Updated 6 years ago
- ☆12Jun 11, 2021Updated 5 years ago
- This adds partial support of AVX2 and AVX-512 to gem5.☆15Dec 19, 2023Updated 2 years ago
- A Feishu/Lark AI agent bot☆16Feb 27, 2026Updated 8 months ago
- Agent Skills from Official Dev Teams and the Community☆12May 24, 2026Updated 5 months ago
- 不围棋c语言实现，大一大作业，关键算法是判断围棋中的气☆10Aug 14, 2020Updated 6 years ago
- TensorRT half precision inference routine on a API-based TensorRT model☆12Jul 3, 2018Updated 8 years ago
- Source code for the architectural and circuit-level simulators used for modeling the CROW (Copy-ROW DRAM) mechanism proposed in our ISCA …☆18Aug 2, 2019Updated 7 years ago
- The repo of "SoK: FHE-Friendly Symmetric Ciphers and Transciphering" (CHES 2025)☆12Apr 8, 2025Updated last year
- 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.
- A straightforward (complete) sample of how to implement AES-GCM by using Linux crypto API at kernel side☆13Oct 6, 2022Updated 4 years ago
- ☆16Sep 27, 2026Updated last month
- An attempt to migrate Karpathy's llm.c to safe rust.☆14Jun 4, 2024Updated 2 years ago
- ☆12Mar 22, 2022Updated 4 years ago
- Support library for Collaborative Realtime Editing via Operational Transformation☆10Feb 23, 2021Updated 5 years ago
- A Rust compiler backend and runtime that compiles Rust kernels to many NPU/GPU accelerators via MLIR — vendor-agnostic (Ascend, Trainium,…☆20Updated this week
- ☆14Mar 7, 2025Updated last year
Are these results useful?