InnerVault

Library

85,340 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.

Results

  1. LMCache

    AI repositories

    LMCache: Supercharge Your LLM with the Fastest KV Cache Layer

    Indexed GitHub, LMCache 12.4k ★Apache-2.0Updated 2 days ago

    git clone https://github.com/LMCache/LMCache.git
  2. AI-CUDA-Engineer-Archive

    Datasets & benchmarks

    Hugging Face dataset by SakanaAI

    Stale Hugging Face Hub, SakanaAI 236 ♥cc-by-4.0Updated 21 months ago

    SakanaAI/AI-CUDA-Engineer-Archive
  3. pegainfer

    AI repositories

    Pure Rust + CUDA LLM inference engine — no PyTorch, OpenAI-compatible, serves Qwen3 to Kimi-K2

    Stale GitHub, pegainfer-project 729 ★Apache-2.0Updated 18 days ago

    git clone https://github.com/pegainfer-project/pegainfer.git
  4. vllm

    AI repositories

    A high-throughput and memory-efficient inference and serving engine for LLMs

    Indexed GitHub, vllm-project 97.0k ★Apache-2.0Updated today

    git clone https://github.com/vllm-project/vllm.git
  5. lmdeploy

    AI repositories

    LMDeploy is a toolkit for compressing, deploying, and serving LLMs.

    Stale GitHub, InternLM 8,136 ★Apache-2.0Updated 6 days ago

    git clone https://github.com/InternLM/lmdeploy.git
  6. sglang

    AI repositories

    SGLang is a high-performance serving framework for large language models and multimodal models.

    Indexed GitHub, sgl-project 38.9k ★Apache-2.0Updated today

    git clone https://github.com/sgl-project/sglang.git
  7. skills

    AI repositories

    Agent Skills for NVIDIA products — install into Claude Code, Codex, and other coding agents to run Physical AI, robotics, simulation, CUDA, and RAG workflows end to end.

    Indexed GitHub, NVIDIA 4,010 ★Apache-2.0Updated yesterday

    git clone https://github.com/NVIDIA/skills.git
  8. text generation model by prism-ml · llama.cpp

    Indexed Hugging Face Hub, prism-ml 3,027 ♥apache-2.0Updated 12 days ago

    prism-ml/Ternary-Bonsai-2-27B-gguf
  9. Evidence-driven CUDA, CUTLASS, Triton and GPU workload optimization for ChatGPT · 使用 ChatGPT 驱动 GPU workload 性能优化

    Stale GitHub, troycheng 7 ★MITUpdated 12 days ago

    git clone https://github.com/troycheng/cuda-kernel-optimizer.git
  10. Breeze-TTS-2

    Models

    text to speech model by BreezeBlue · transformers

    Indexed Hugging Face Hub, BreezeBlue 988 ♥otherUpdated 2 months ago

    BreezeBlue/Breeze-TTS-2
  11. text generation model by Edge0 · edge0

    Indexed Hugging Face Hub, Edge0 355 ♥otherUpdated yesterday

    Edge0/Edge0-145B-NVFP4
  12. surogate

    AI repositories

    Train and serve LLMs at extreme speed and massive throughput.

    Stale GitHub, invergent-ai 885 ★Apache-2.0Updated 11 days ago

    git clone https://github.com/invergent-ai/surogate.git
  13. text generation model by prism-ml · llama.cpp

    Stale Hugging Face Hub, prism-ml 796 ♥apache-2.0Updated 7 months ago

    prism-ml/Bonsai-8B-gguf
  14. text generation model by prism-ml · llama.cpp

    Indexed Hugging Face Hub, prism-ml 1,449 ♥apache-2.0Updated 2 months ago

    prism-ml/Ternary-Bonsai-27B-gguf
  15. ds4-on-spark

    Datasets & benchmarks

    Entrpi/ds4, a Blackwell CUDA perf fork of antirez/ds4 on NVIDIA DGX Spark: one-command install, ~3x upstream prefill, ~1.5x decode, DSpark, and full continuous batch support

    Stale GitHub, Entrpi 409 ★MITUpdated 2 months ago

    git clone https://github.com/Entrpi/ds4-on-spark.git
  16. llm-algo-leetcode

    Docs & tutorials

    Hands-on LLM algorithms and systems with PyTorch, Triton & CUDA.《大模型算法与系统教程》:模型架构与训练、后训练、推理加速、性能与算子优化,配套 Notebook 练习、答案解析、测试与实验。

    Indexed GitHub, datawhalechina 794 ★Custom licence (see repository)Updated today

    git clone https://github.com/datawhalechina/llm-algo-leetcode.git
  17. text generation model by prism-ml · llama.cpp

    Stale Hugging Face Hub, prism-ml 920 ♥apache-2.0Updated 4 months ago

    prism-ml/Bonsai-27B-gguf
  18. tt-metal

    AI repositories

    :metal: TT-NN operator library, and TT-Metalium low level kernel programming model.

    Stale GitHub, tenstorrent 1,747 ★Apache-2.0Updated 8 days ago

    git clone https://github.com/tenstorrent/tt-metal.git
  19. image text to text model by huihui-ai · transformers

    Indexed Hugging Face Hub, huihui-ai 2,214 ♥apache-2.0Updated yesterday

    huihui-ai/Huihui-Qwen3.8-27B-abliterated-GGUF
  20. cuda-mcp

    MCP servers

    CUDA MCP: 20 real tools to read, check, lint, scaffold, build and run CUDA code.

    Stale Official MCP Registry, io.github.mrfentmen Updated 8 days ago 1 note

    @mrfentmen/cuda-mcp@1.0.0
  21. TensorFold

    AI repositories

    LLM Inference Engine for Metal, CUDA and Vulkan.

    Indexed GitHub, ashhart 2,266 ★Apache-2.0Updated today

    git clone https://github.com/ashhart/TensorFold.git
  22. gpustack

    AI repositories

    A GPU cluster manager for high-performance AI model serving (vLLM, SGLang) and on-demand SSH-accessible GPU instances.

    Indexed GitHub, gpustack 6,039 ★Apache-2.0Updated 3 days ago

    git clone https://github.com/gpustack/gpustack.git
  23. inferssd

    AI repositories

    Run models larger than your RAM or VRAM by streaming MoE experts from SSD. Built on llama.cpp.

    Indexed GitHub, wici-ai 1,025 ★Apache-2.0Updated 3 days ago

    git clone https://github.com/wici-ai/inferssd.git
  24. raft

    AI repositories

    RAFT contains fundamental widely-used algorithms and primitives for machine learning and information retrieval. The algorithms are CUDA-accelerated and form building blocks for more easily writing high performance applications.

    Stale GitHub, NVIDIA 1,051 ★Apache-2.0Updated 13 days ago

    git clone https://github.com/NVIDIA/raft.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.