Search Results for "vllm"
Sort By:
Showing 104 open source projects for "vllm"
View related business solutions-
99.99% Uptime for MySQL and PostgreSQL DatabasesCloud SQL Enterprise Plus delivers near-zero downtime with 35 days of point-in-time recovery. Supports MySQL, PostgreSQL, and SQL Server.
-
Go from Code to Production URL in SecondsSkip the Kubernetes configs. Cloud Run handles HTTPS, scaling, and infrastructure automatically. Two million requests free per month.
-
1
vLLM
A high-throughput and memory-efficient inference and serving engine
vLLM is a fast and easy-to-use library for LLM inference and serving. High-throughput serving with various decoding algorithms, including parallel sampling, beam search, and more. -
2
Nano-vLLM
A lightweight vLLM implementation built from scratch
...Its API closely mirrors that of the original vLLM framework, allowing developers familiar with vLLM to adopt the tool with minimal changes. -
3
vLLM Semantic Router
System Level Intelligent Router for Mixture-of-Models at Cloud
Semantic Router is an open-source system designed to intelligently route requests across multiple large language models based on the semantic meaning and complexity of user queries. Instead of sending every prompt to the same model, the system analyzes the intent and reasoning requirements of the request and dynamically selects the most appropriate model to process it. This approach allows developers to combine multiple models with different strengths, such as lightweight models for simple... -
4
Qwen-Image-2.1
Qwen's most powerful open-source image generation model
...It supports native 2K output across multiple aspect ratios while improving typography, portrait lighting, textures, and fine details. Efficient inference features include mixed-granularity attention, prefix KV caching, model offloading, and integrations with Diffusers, ComfyUI, vLLM, SGLang, and LightX2V. -
MongoDB Atlas runs apps anywhereMongoDB Atlas gives you the freedom to build and run modern applications anywhere—across AWS, Azure, and Google Cloud. With global availability in over 115 regions, Atlas lets you deploy close to your users, meet compliance needs, and scale with confidence across any geography.
-
5
OpenJarvis
Personal AI, On Personal Devices
...The framework provides shared primitives for building local-first agents, along with evaluation tools that measure performance using metrics such as energy consumption, latency, cost, and accuracy. OpenJarvis integrates with local inference engines like Ollama, vLLM, SGLang, and llama.cpp to run language models directly on personal hardware. It also includes a learning loop that allows models to improve over time using locally generated interaction traces. By prioritizing local execution and efficiency, OpenJarvis aims to provide a foundation for privacy-preserving personal AI assistants. -
6
Unlimited OCR Works
Welcome the Era of One-shot Long-horizon Parsing
...The project supports single-image parsing as well as multi-page and PDF-style parsing by converting pages into images. It provides inference paths for Hugging Face Transformers, vLLM, and SGLang, which gives users several deployment options. The repository also includes example code for batch inference over image folders or PDF inputs. Overall, it is useful for researchers and developers who need advanced OCR, long-document parsing, and model-based extraction from complex visual documents. -
7
DeepSeek-OCR 2
Visual Causal Flow
...The repository provides model code and inference scripts that let researchers and developers run and benchmark the system on both images and PDFs, with support for batch evaluation and optimized pipelines leveraging vLLM and transformers. -
8
GLM-5.1
GLM-5: From Vibe Coding to Agentic Engineering
...The model leverages large-scale pretraining, reinforcement learning infrastructure, and sparse attention mechanisms to improve efficiency while maintaining strong long-context understanding. It supports deployment through frameworks such as vLLM, SGLang, xLLM, and KTransformers, enabling scalable local inference for enterprise and research use cases. -
9
Halo
Framework built by White Circle for training large language
...Distributed execution supports expert, context, tensor, and expert-tensor parallelism alongside FSDP2. Performance features include FlashAttention, DeepEP, Liger kernels, Grouped GEMM, BF16 optimizers, LoRA, and QLoRA. RL rollouts can run through vLLM or SGLang while overlapping with training. Halo also provides Docker images, YAML recipes, checkpoint tools, dataset utilities, benchmarks, and agent-oriented technical documentation. -
Veeam Data Platform v13.1Try Veeam Data Platform today. Experience the unified platform that's secure by design, portable by default, and proven to recover clean, fast, and anywhere.
-
10
Harbor LLM
Run a full local LLM stack with one command using Docker
...With a single command, users can start preconfigured tools like Ollama and Open WebUI, enabling chat, workflows, and integrations immediately. Harbor supports multiple inference engines, including llama.cpp and vLLM, and connects them seamlessly to user interfaces. It also includes tools for web retrieval, image generation, voice interaction, and workflow automation. Built on Docker, Harbor allows services to run in isolated containers while communicating over a local network. It is intended for local development and experimentation rather than production deployment, giving developers a flexible way to explore AI systems, test configurations, and manage complex LLM stacks without manual wiring or setup overhead. -
11
NVIDIA Model Optimizer
A unified library of SOTA model optimization techniques
...It supports a wide range of model types, including large language models, diffusion models, and vision-language models, and integrates with deployment frameworks such as TensorRT and vLLM. By providing standardized workflows and APIs, it enables developers to experiment with different optimization strategies and select the best approach for their use case. -
12
KubeAI
Private Open AI on Kubernetes
...KubeAI serves an OpenAI compatible HTTP API. Admins can configure ML models by using the Model Kubernetes Custom Resources. KubeAI can be thought of as a Model Operator (See Operator Pattern) that manages vLLM and Ollama servers. -
13
Kimi K2.5
Moonshot's most powerful AI model
...With a 256K context length and MoonViT vision encoder, the model excels across reasoning, coding, long-context comprehension, image, and video benchmarks. Kimi K2.5 is available via Moonshot’s API (OpenAI/Anthropic-compatible) and supports deployment through vLLM, SGLang, and KTransformers. -
14
Kimi Linear
An expressive, efficient attention architecture
...The models were trained on 5.7 trillion tokens and can reduce KV cache requirements by up to 75 percent. Kimi Linear supports inference through Hugging Face Transformers and deployment as an OpenAI-compatible API with vLLM. -
15
TokenSpeed
TokenSpeed is a speed-of-light LLM inference engine
TokenSpeed is an LLM inference engine designed for high-performance production agent workloads. It aims to combine TensorRT-LLM-level speed with vLLM-level usability, making it relevant for teams that need fast generation without sacrificing developer ergonomics. The project is focused on the specific needs of agentic systems, where latency, throughput, and efficient scheduling matter across many short or tool-heavy requests. It builds on ideas and components from the broader open-source inference ecosystem while presenting its own execution stack. ... -
16
NemoClaw
NVIDIA plugin for secure installation of OpenClaw
...NemoClaw enables users to launch sandboxed agent environments that control network access, file permissions, and inference requests through policy-based security. The platform integrates with AI models such as NVIDIA Nemotron and supports multiple inference backends including cloud APIs, local NIM deployments, and vLLM. Through its command-line interface, developers can deploy, monitor, and manage AI assistants running inside isolated sandboxes. By combining sandbox orchestration, agent management, and AI model integration, NemoClaw provides a secure foundation for building and operating autonomous AI assistants. -
17
Intel LLM Library for PyTorch
Accelerate local LLM inference and finetuning
...IPEX-LLM supports a wide range of popular models, including architectures such as LLaMA, Mistral, Qwen, and other transformer-based systems. The library can integrate with common AI frameworks and serving tools such as Hugging Face Transformers, LangChain, and vLLM, allowing developers to incorporate optimized inference into existing pipelines. -
18
GLM-4.5
GLM-4.5: Open-source LLM for intelligent agents by Z.ai
...GLM-4.5 achieves strong performance on 12 industry-standard benchmarks, ranking 3rd overall, while GLM-4.5-Air balances competitive results with greater efficiency. The models support FP8 and BF16 precision, and can handle very large context windows of up to 128K tokens. Flexible inference is supported through frameworks like vLLM and SGLang with tool-call and reasoning parsers included. -
19
Orpheus TTS
Towards Human-Sounding Speech
...The project ships both pretrained and finetuned English models, as well as a family of multilingual models released as a research preview, and includes data-processing scripts so users can train or finetune their own variants. Inference is provided through a Python package that uses vLLM under the hood for high-throughput, low-latency generation, including streaming examples that show how to generate audio chunks in real time. The maintainers provide Colab notebooks, a standardized prompting format, and one-click deployment via Baseten for production-grade, FP8/FP16 optimized inference with ~200 ms streaming latency. -
20
GLM-5
From Vibe Coding to Agentic Engineering
GLM-5 is a next-generation open-source large language model (LLM) developed by the Z .ai team under the zai-org organization that pushes the boundaries of reasoning, coding, and long-horizon agentic intelligence. Building on earlier GLM series models, GLM-5 dramatically scales the parameter count (to roughly 744 billion) and expands pre-training data to significantly improve performance on complex tasks such as multi-step reasoning, software engineering workflows, and agent orchestration... -
21
OuteTTS
Interface for OuteTTS models
...It provides a high-level Interface API that wraps model configuration, speaker handling, and audio generation so you can focus on integrating speech into your application rather than wiring up low-level engines. The project supports multiple backends including llama.cpp (Python bindings and server), Hugging Face Transformers, ExLlamaV2, VLLM and a JavaScript interface via Transformers.js, allowing it to run on CPUs, NVIDIA CUDA GPUs, AMD ROCm, Vulkan-capable GPUs, and Apple Metal. It also includes a notion of speaker profiles: you can create a speaker from a short audio sample, save it as JSON, and reuse it for consistent voice identity across generations and sessions. ... -
22
LocalAI
The free, Open Source alternative to OpenAI, Claude and others
LocalAI is an open-source platform that allows users to run large language models and other AI systems locally on their own hardware. It acts as a drop-in replacement for APIs such as OpenAI, enabling developers to build AI-powered applications without relying on external cloud services. The platform supports a wide range of model types, including text generation, image creation, speech processing, and embeddings. LocalAI can run on consumer-grade hardware and does not necessarily require a... -
23
DocsGPT
Private AI agents, assistants and search over your own documents
...Agents call tools, APIs and MCP servers with per-action approval; a visual builder chains AI steps, conditions and code into workflows; agents can produce DOCX, XLSX, PPTX and PDF files. Models: OpenAI, Anthropic, Google and others, or local via Ollama, llama.cpp or vLLM. Vectors: pgvector, Qdrant, Milvus, Elasticsearch, MongoDB Atlas or FAISS. Install with one line (curl -fsSL https://docs.ac/install | bash), or deploy with Docker Compose or Kubernetes, including fully air-gapped. Ships an OpenAI-compatible API, an MCP server, a chat widget, OIDC SSO, SCIM, guardrails and an audit log. -
24
Void Editor
Open source AI IDE and Cursor alternative
Void is an open-source, AI-powered code editor built as a fork of Visual Studio Code. Designed as a fully transparent and privacy-focused alternative to Cursor or GitHub Copilot, it lets you use AI models locally or via APIs (OpenAI, Claude, Gemini, Ollama, etc.)—without routing data through proprietary servers. Developed by YC-backed startup Glass Devtools, it supports traditional coding features inherited from VS Code, enhanced with in-editor LLM capabilities—autocomplete, inline quick... -
25
Hy-MT2 is a family of fast-thinking multilingual translation models built for complex real-world translation scenarios. It includes 1.8B, 7B, and 30B-A3B model sizes, giving users options for lightweight deployment, stronger general performance, or MoE-based capacity. The models support translation across 33 languages and are designed to follow detailed translation instructions in multiple languages. They can handle tasks involving terminology, style, personalization, delimiters, structured...
