Library
85,762 resources from 11 public sources. 53 checked by hand; the rest are unreviewed.
Results
-
sglang
AI repositoriesSGLang is a high-performance serving framework for large language models and multimodal models.
git clone https://github.com/sgl-project/sglang.git -
zero-to-sglang
Docs & tutorialsOfficial SGLang x Datawhale course on LLM inference: understand inference, build a mini-sglang from scratch, then read the real SGLang source and land your first PR. Available in English and Chinese.
git clone https://github.com/datawhalechina/zero-to-sglang.git -
Cosmos3-Nano
Modelsmodel by nvidia · cosmos
nvidia/Cosmos3-Nano -
SpecForge
AI repositoriesTrain speculative decoding models effortlessly and port them smoothly to SGLang serving.
git clone https://github.com/sgl-project/SpecForge.git -
gpustack
AI repositoriesA GPU cluster manager for high-performance AI model serving (vLLM, SGLang) and on-demand SSH-accessible GPU instances.
git clone https://github.com/gpustack/gpustack.git -
MiniMax-Music3
Modelstext to audio model by MiniMaxAI · diffusers
MiniMaxAI/MiniMax-Music3 -
Mooncake
AI repositoriesMooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI.
git clone https://github.com/kvcache-ai/Mooncake.git -
Bittune
Agents & frameworksLocal-first engineering agent that deploys, benchmarks and tunes vLLM/SGLang inference services on your own GPUs, with auditable run evidence.
git clone https://github.com/bitcloud-ai/Bittune.git -
Qwen3.8-27B-DSpine-b16
Modelstext generation model by tencent
tencent/Qwen3.8-27B-DSpine-b16 -
ome
AI repositoriesOpen Model Engine (OME) — Kubernetes operator for LLM serving, GPU scheduling, and model lifecycle management. Works with SGLang, vLLM, TensorRT-LLM, and Triton
git clone https://github.com/ome-projects/ome.git -
MemT-1.0
Agents & frameworksOfficial repository for MemT-1.0
git clone https://github.com/MemTensor/MemT-1.0.git -
Mistral-Large-4-1T-A52B
Modelsimage text to text model by mistralai · transformers
mistralai/Mistral-Large-4-1T-A52B -
Qwen3.8-27B-DFlash2
Modelstext generation model by z-lab · transformers
z-lab/Qwen3.8-27B-DFlash2 -
kvcached
AI repositoriesVirtualized Elastic KV Cache for Dynamic GPU Sharing and Beyond
git clone https://github.com/ovg-project/kvcached.git -
One-Eval
Datasets & benchmarksAutomated system for LLM evaluation via agents. Doc as below:
git clone https://github.com/OpenDCAI/One-Eval.git -
smg
AI repositoriesEngine-agnostic LLM gateway in Rust. Full OpenAI & Anthropic API compatibility across vLLM, TRT-LLM, TokenSpeed, SGLang, OpenAI, Gemini & more. Industry-first gRPC pipeline, KV cache-aware routing, chat history, tokenization caching, Responses API, embeddings, WASM plugins, MCP, and multi-tenant auth.
git clone https://github.com/smg-project/smg.git -
Qwen3.8-Flash-Next-DFlash2
Modelstext generation model by incoai · transformers
incoai/Qwen3.8-Flash-Next-DFlash2 -
model by mistralai
mistralai/Mistral-Large-4-1T-A52B-NVFP4 -
Mistral-Large-4-1T-A52B-GGUF
Modelsmodel by unsloth · transformers
unsloth/Mistral-Large-4-1T-A52B-GGUF -
MiniMax-H3-Image-PE
Modelstext generation model by MiniMaxAI · transformers
MiniMaxAI/MiniMax-H3-Image-PE -
inference
AI repositoriesOpen-source inference platform for language, vision, embedding, reranking, image, audio, and video models. Deploy with multiple engines across heterogeneous hardware, from a laptop to a distributed cluster. Serve models through OpenAI-compatible APIs.
git clone https://github.com/xorbitsai/inference.git -
Hyperloom
Agents & frameworksAn agentic system that auto-optimizes LLM workloads on AMD GPUs.
git clone https://github.com/AMD-AGI/Hyperloom.git -
image text to text model by drowzeys · transformers
drowzeys/keys-DeepSeek-V4.1-Flash-1017-Abliterated -
skills
SkillsClaude Code plugin marketplace — 77 installable reference skills across vLLM/SGLang inference, Kubernetes & Harvester, GPU host bring-up, observability, security, and agent workflows.
git clone https://github.com/air-gapped/skills.git
Indexed entries aren't reviewed or tested by InnerVault. Details come straight from each source. Anything that can reach your accounts, files or browser can do damage, so read the source before you install it.