Lsglang is a special extension of sglang that fully utilizes CPU and GPU computing resources with an efficient GPU parallel + NUMA parallel architecture, suitable for MOE model hybrid inference.
☆142Oct 1, 2026Updated this week
Alternatives and similar repositories for Lsglang
Users that are interested in Lsglang are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- LvLLM is a special NUMA extension of vllm that makes full use of CPU and memory resources, reduces GPU memory requirements, and features …☆462Sep 22, 2026Updated last week
- 大语言模型工具集☆28Aug 1, 2025Updated last year
- vllm混合推理扩展插件，支持多NUMA混合推理，单卡推理Qwen3-Next模型可达1000+ prefill☆34Nov 7, 2025Updated 10 months ago
- Qwen4-Exp (Qwen3.8-Flash-Next) SWA + MTP + PLE-on-iswa — bounded deep-context decode w/ long-range recall, TBQ4 4.25 bpv KV, DSpark + Rot…☆95Sep 24, 2026Updated last week
- forked from vllm-project/flash-attention☆66May 9, 2026Updated 4 months ago
- GPU virtual machines on DigitalOcean Gradient AI • AdGet to production fast with high-performance AMD and NVIDIA GPUs you can spin up in seconds. The definition of operational simplicity.
- Unlock P2P comms between consumer NVIDIA GPUs☆559Sep 16, 2026Updated 2 weeks ago
- VCP visual-synesthesia plugin v2 for DeepSeek Harness (official Slot API): raw-HTML vcp-root cards, streaming render, KaTeX/Mermaid/SVG, …☆56Sep 4, 2026Updated 3 weeks ago
- A source repo of Postgres Chinese full-test search docker image, based on zhparser.☆10Mar 25, 2021Updated 5 years ago
- llama.cpp fork with additional SOTA quants and improved performance☆3,272Updated this week
- RIFT 见缝插帧☆17May 15, 2022Updated 4 years ago
- Run DeepSeek-V4.1-Flash / DeepSeek-V4-Flash and GLM-5.3-Flash on SM89 (Ada / RTX 4090) and SM120 (RTX PRO 6000) with vLLM☆177Updated this week
- Precision Knowledge Editing (PKE): A novel method to reduce toxicity in LLMs while preserving performance, with robust evaluations and ha…☆12Nov 26, 2024Updated last year
- a demo of Animeganv2 infer by ncnn☆23Nov 26, 2021Updated 4 years ago
- ComfyUI custom node for Qwen3.5-9B unified multimodal model☆40Mar 13, 2026Updated 6 months ago
- GPU virtual machines on DigitalOcean Gradient AI • AdGet to production fast with high-performance AMD and NVIDIA GPUs you can spin up in seconds. The definition of operational simplicity.
- 检测透视图像中的矩形文档并对其进行矫正☆32Sep 16, 2022Updated 4 years ago
- ☆16Jan 23, 2022Updated 4 years ago
- Tries to UI development. Clone of https://www.perplexity.ai/☆11Sep 30, 2023Updated 3 years ago
- Use ‘DICE-Talk’ in ComfyUI，which is a method about 'Correlation-Aware Emotional Talking Portrait Generation'.☆24May 7, 2025Updated last year
- enable Clawdbot to support tool calling functionality for local inference models (sglang/vLLM). Duckduckgo api-free web-search tool is av…☆19Feb 6, 2026Updated 7 months ago
- ☆14Sep 4, 2024Updated 2 years ago
- Probably one of the lightest native RAG + Agent apps out there，experience the power of Agent-powered models and Agent-driven knowledge ba…☆33May 30, 2025Updated last year
- Framework for testing the reachability of native functions in Android applications.☆11Aug 30, 2023Updated 3 years ago
- ☆974Sep 14, 2025Updated last year
- 1-Click AI Models by DigitalOcean Gradient • AdDeploy popular AI models on DigitalOcean Gradient GPU virtual machines with just a single click. Zero configuration with optimized deployments.
- llama.cpp fork with TQ3_1S/4S CUDA kernels — 3.5-bit WHT quantization achieving Q4s quality at 10% smaller size. Based on RaBitQ-inspired…☆232Updated this week
- Xposed module that hooks into various HTTP libraries to log network calls.☆13Jan 4, 2023Updated 3 years ago
- Hopenet: deep head pose estimator on ncnn☆10Jun 18, 2020Updated 6 years ago
- ☆10Jan 29, 2021Updated 5 years ago
- Large-scale exact string matching tool☆17Mar 7, 2025Updated last year
- The open-source operating system for robots — install it and your robot comes alive☆375Updated this week
- Challenging SAT benchmarks for matrix multiplication☆13Oct 28, 2021Updated 4 years ago
- KTransformers 一键部署脚本☆60Apr 18, 2025Updated last year
- Unofficial ComfyUI implementation of UniWorld.☆22Jun 10, 2025Updated last year
- Wordpress hosting with auto-scaling - Free Trial Offer • AdFully Managed hosting for WordPress and WooCommerce businesses that need reliable, auto-scalable performance. Cloudways SafeUpdates now available.
- AI智能助理前端组件,聊天助手前端组件,AI组件☆36Jun 15, 2026Updated 3 months ago
- FORK of VLLM for AMD MI25/50/60. A high-throughput and memory-efficient inference and serving engine for LLMs☆70May 4, 2025Updated last year
- 基于传统方法(非深度学习)的美颜算法实现，支持美白和磨皮☆13Jul 31, 2023Updated 3 years ago
- FlashInfer: Kernel Library for LLM Serving (Windows build & kernels)☆19Jul 1, 2026Updated 3 months ago
- PiDiNet running in Android by ncnn☆15Sep 26, 2021Updated 5 years ago
- qrencode for openresty☆11Sep 21, 2017Updated 9 years ago
- matrix_calculus☆10Aug 4, 2022Updated 4 years ago