LocalAI/backend/index.yaml

---
## vLLM
- &vllm
  name: "cuda11-vllm"
  uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-11-vllm"
  license: apache-2.0
  urls:
    - https://github.com/vllm-project/vllm
  tags:
    - text-to-text
    - multimodal
    - GPTQ
    - AWQ
    - AutoRound
    - INT4
    - INT8
    - FP8
  icon: https://raw.githubusercontent.com/vllm-project/vllm/main/docs/assets/logos/vllm-logo-text-dark.png
  description: |
    vLLM is a fast and easy-to-use library for LLM inference and serving.
    Originally developed in the Sky Computing Lab at UC Berkeley, vLLM has evolved into a community-driven project with contributions from both academia and industry.
    vLLM is fast with:
        State-of-the-art serving throughput
        Efficient management of attention key and value memory with PagedAttention
        Continuous batching of incoming requests
        Fast model execution with CUDA/HIP graph
        Quantizations: GPTQ, AWQ, AutoRound, INT4, INT8, and FP8
        Optimized CUDA kernels, including integration with FlashAttention and FlashInfer
        Speculative decoding
        Chunked prefill
  alias: "vllm"
- !!merge <<: *vllm
  name: "cuda12-vllm"
  uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-12-vllm"
- !!merge <<: *vllm
  name: "rocm-vllm"
  uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-rocm-hipblas-vllm"
- !!merge <<: *vllm
  name: "intel-sycl-f32-vllm"
  uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-intel-sycl-f32-vllm"
- !!merge <<: *vllm
  name: "intel-sycl-f16-vllm"
  uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-intel-sycl-f16-vllm"
- !!merge <<: *vllm
  name: "cuda11-vllm-development"
  uri: "quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-11-vllm"
- !!merge <<: *vllm
  name: "cuda12-vllm-development"
  uri: "quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-12-vllm"
- !!merge <<: *vllm
  name: "rocm-vllm-development"
  uri: "quay.io/go-skynet/local-ai-backends:master-gpu-rocm-hipblas-vllm"
- !!merge <<: *vllm
  name: "intel-sycl-f32-vllm-development"
  uri: "quay.io/go-skynet/local-ai-backends:master-gpu-intel-sycl-f32-vllm"
- !!merge <<: *vllm
  name: "intel-sycl-f16-vllm-development"
  uri: "quay.io/go-skynet/local-ai-backends:master-gpu-intel-sycl-f16-vllm"
## Rerankers
- name: "cuda11-rerankers"
  uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-11-rerankers"
  alias: "cuda11-rerankers"
- name: "cuda12-rerankers"
  uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-12-rerankers"
  alias: "cuda12-rerankers"
- name: "intel-sycl-f32-rerankers"
  uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-intel-sycl-f32-rerankers"
  alias: "intel-sycl-f32-rerankers"
- name: "intel-sycl-f16-rerankers"
  uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-intel-sycl-f16-rerankers"
  alias: "intel-sycl-f16-rerankers"
- name: "rocm-rerankers"
  uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-rocm-hipblas-rerankers"
  alias: "rocm-rerankers"
- name: "cuda11-rerankers-development"
  uri: "quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-11-rerankers"
  alias: "rerankers"

- name: "cuda12-rerankers-development"
  uri: "quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-12-rerankers"
  alias: "rerankers"
- name: "rocm-rerankers-development"
  uri: "quay.io/go-skynet/local-ai-backends:master-gpu-rocm-hipblas-rerankers"
  alias: "rerankers"

- name: "intel-sycl-f32-rerankers-development"
  uri: "quay.io/go-skynet/local-ai-backends:master-gpu-intel-sycl-f32-rerankers"
  alias: "rerankers"

- name: "intel-sycl-f16-rerankers-development"
  uri: "quay.io/go-skynet/local-ai-backends:master-gpu-intel-sycl-f16-rerankers"
  alias: "rerankers"
## Transformers
- &transformers
  name: "cuda12-transformers"
  uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-12-transformers"
  icon: https://camo.githubusercontent.com/26569a27b8a30a488dd345024b71dbc05da7ff1b2ba97bb6080c9f1ee0f26cc7/68747470733a2f2f68756767696e67666163652e636f2f64617461736574732f68756767696e67666163652f646f63756d656e746174696f6e2d696d616765732f7265736f6c76652f6d61696e2f7472616e73666f726d6572732f7472616e73666f726d6572735f61735f615f6d6f64656c5f646566696e6974696f6e2e706e67
  alias: "transformers"
  license: apache-2.0
  description: |
    Transformers acts as the model-definition framework for state-of-the-art machine learning models in text, computer vision, audio, video, and multimodal model, for both inference and training.
    It centralizes the model definition so that this definition is agreed upon across the ecosystem. transformers is the pivot across frameworks: if a model definition is supported, it will be compatible with the majority of training frameworks (Axolotl, Unsloth, DeepSpeed, FSDP, PyTorch-Lightning, ...), inference engines (vLLM, SGLang, TGI, ...), and adjacent modeling libraries (llama.cpp, mlx, ...) which leverage the model definition from transformers.
  urls:
    - https://github.com/huggingface/transformers
  tags:
    - text-to-text
    - multimodal
- !!merge <<: *transformers
  name: "rocm-transformers"
  uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-rocm-hipblas-transformers"
- !!merge <<: *transformers
  name: "intel-sycl-f32-transformers"
  uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-intel-sycl-f32-transformers"
- !!merge <<: *transformers
  name: "intel-sycl-f16-transformers"
  uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-intel-sycl-f16-transformers"
- !!merge <<: *transformers
  name: "cuda11-transformers-development"
  uri: "quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-11-transformers"
- !!merge <<: *transformers
  name: "cuda11-transformers"
  uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-11-transformers"
- !!merge <<: *transformers
  name: "cuda12-transformers-development"
  uri: "quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-12-transformers"
- !!merge <<: *transformers
  name: "rocm-transformers-development"
  uri: "quay.io/go-skynet/local-ai-backends:master-gpu-rocm-hipblas-transformers"
- !!merge <<: *transformers
  name: "intel-sycl-f32-transformers-development"
  uri: "quay.io/go-skynet/local-ai-backends:master-gpu-intel-sycl-f32-transformers"
- !!merge <<: *transformers
  name: "intel-sycl-f16-transformers-development"
  uri: "quay.io/go-skynet/local-ai-backends:master-gpu-intel-sycl-f16-transformers"
## Diffusers
- &diffusers
  icon: https://raw.githubusercontent.com/huggingface/diffusers/main/docs/source/en/imgs/diffusers_library.jpg
  description: |
    🤗 Diffusers is the go-to library for state-of-the-art pretrained diffusion models for generating images, audio, and even 3D structures of molecules. Whether you're looking for a simple inference solution or training your own diffusion models, 🤗 Diffusers is a modular toolbox that supports both.
  urls:
    - https://github.com/huggingface/diffusers
  tags:
    - image-generation
    - video-generation
    - diffusion-models
  name: "cuda12-diffusers"
  license: apache-2.0
  uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-12-diffusers"
  alias: "diffusers"
- !!merge <<: *diffusers
  name: "rocm-diffusers"
  uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-rocm-hipblas-diffusers"
- !!merge <<: *diffusers
  name: "cuda11-diffusers"
  uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-11-diffusers"
- !!merge <<: *diffusers
  name: "intel-sycl-f32-diffusers"
  uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-intel-sycl-f32-diffusers"
- !!merge <<: *diffusers
  name: "cuda11-diffusers-development"
  uri: "quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-11-diffusers"
- !!merge <<: *diffusers
  name: "cuda12-diffusers-development"
  uri: "quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-12-diffusers"
- !!merge <<: *diffusers
  name: "rocm-diffusers-development"
  uri: "quay.io/go-skynet/local-ai-backends:master-gpu-rocm-hipblas-diffusers"
- !!merge <<: *diffusers
  name: "intel-sycl-f32-diffusers-development"
  uri: "quay.io/go-skynet/local-ai-backends:master-gpu-intel-sycl-f32-diffusers"
  ## exllama2
- &exllama2
  urls:
    - https://github.com/turboderp-org/exllamav2
  tags:
    - text-to-text
    - LLM
    - EXL2
  license: MIT
  description: |
    ExLlamaV2 is an inference library for running local LLMs on modern consumer GPUs.
  name: "cuda11-exllama2"
  uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-11-exllama2"
  alias: "exllama2"
- !!merge <<: *exllama2
  name: "cuda12-exllama2"
  uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-12-exllama2"
- !!merge <<: *exllama2
  name: "cuda11-exllama2-development"
  uri: "quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-11-exllama2"
- !!merge <<: *exllama2
  name: "cuda12-exllama2-development"
  uri: "quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-12-exllama2"
## kokoro
- &kokoro
  icon: https://avatars.githubusercontent.com/u/166769057?v=4
  description: |
    Kokoro is an open-weight TTS model with 82 million parameters. Despite its lightweight architecture, it delivers comparable quality to larger models while being significantly faster and more cost-efficient. With Apache-licensed weights, Kokoro can be deployed anywhere from production environments to personal projects.
  urls:
    - https://huggingface.co/hexgrad/Kokoro-82M
    - https://github.com/hexgrad/kokoro
  tags:
    - text-to-speech
    - TTS
    - LLM
  license: apache-2.0
  name: "cuda11-kokoro-development"
  uri: "quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-11-kokoro"
  alias: "kokoro"
- !!merge <<: *kokoro
  name: "cuda12-kokoro-development"
  uri: "quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-12-kokoro"
- !!merge <<: *kokoro
  name: "rocm-kokoro-development"
  uri: "quay.io/go-skynet/local-ai-backends:master-gpu-rocm-hipblas-kokoro"
- !!merge <<: *kokoro
  name: "sycl-f32-kokoro"
  uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-intel-sycl-f32-kokoro"
- !!merge <<: *kokoro
  name: "sycl-f16-kokoro"
  uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-intel-sycl-f16-kokoro"
- !!merge <<: *kokoro
  name: "sycl-f16-kokoro-development"
  uri: "quay.io/go-skynet/local-ai-backends:master-gpu-intel-sycl-f16-kokoro"
- !!merge <<: *kokoro
  name: "sycl-f32-kokoro-development"
  uri: "quay.io/go-skynet/local-ai-backends:master-gpu-intel-sycl-f32-kokoro"
## faster-whisper
- &faster-whisper
  icon: https://avatars.githubusercontent.com/u/1520500?s=200&v=4
  description: |
    faster-whisper is a reimplementation of OpenAI's Whisper model using CTranslate2, which is a fast inference engine for Transformer models.
    This implementation is up to 4 times faster than openai/whisper for the same accuracy while using less memory. The efficiency can be further improved with 8-bit quantization on both CPU and GPU.
  urls:
    - https://github.com/SYSTRAN/faster-whisper
  tags:
    - speech-to-text
    - Whisper
  license: MIT
  name: "cuda11-faster-whisper-development"
  uri: "quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-11-faster-whisper"
  alias: "faster-whisper"
- !!merge <<: *faster-whisper
  name: "cuda12-faster-whisper-development"
  uri: "quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-12-faster-whisper"
- !!merge <<: *faster-whisper
  name: "rocm-faster-whisper-development"
  uri: "quay.io/go-skynet/local-ai-backends:master-gpu-rocm-hipblas-faster-whisper"
- !!merge <<: *faster-whisper
  name: "sycl-f32-faster-whisper"
  uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-intel-sycl-f32-faster-whisper"
- !!merge <<: *faster-whisper
  name: "sycl-f16-faster-whisper"
  uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-intel-sycl-f16-faster-whisper"
- !!merge <<: *faster-whisper
  name: "sycl-f32-faster-whisper-development"
  uri: "quay.io/go-skynet/local-ai-backends:master-gpu-intel-sycl-f32-faster-whisper"
- !!merge <<: *faster-whisper
  name: "sycl-f16-faster-whisper-development"
  uri: "quay.io/go-skynet/local-ai-backends:master-gpu-intel-sycl-f16-faster-whisper"
## coqui
- &coqui
  urls:
    - https://github.com/idiap/coqui-ai-TTS
  description: |
    🐸 Coqui TTS is a library for advanced Text-to-Speech generation.

    🚀 Pretrained models in +1100 languages.

    🛠️ Tools for training new models and fine-tuning existing models in any language.

    📚 Utilities for dataset analysis and curation.
  tags:
    - text-to-speech
    - TTS
  license: mpl-2.0
  name: "cuda11-coqui-development"
  uri: "quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-11-coqui"
  alias: "coqui"
  icon: https://avatars.githubusercontent.com/u/1338804?s=200&v=4
- !!merge <<: *coqui
  name: "cuda12-coqui-development"
  uri: "quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-12-coqui"
- !!merge <<: *coqui
  name: "rocm-coqui-development"
  uri: "quay.io/go-skynet/local-ai-backends:master-gpu-rocm-hipblas-coqui"
- !!merge <<: *coqui
  name: "sycl-f32-coqui"
  uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-intel-sycl-f32-coqui"
- !!merge <<: *coqui
  name: "sycl-f16-coqui"
  uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-intel-sycl-f16-coqui"
- !!merge <<: *coqui
  name: "sycl-f32-coqui-development"
  uri: "quay.io/go-skynet/local-ai-backends:master-gpu-intel-sycl-f32-coqui"
- !!merge <<: *coqui
  name: "sycl-f16-coqui-development"
  uri: "quay.io/go-skynet/local-ai-backends:master-gpu-intel-sycl-f16-coqui"
## bark
- &bark
  urls:
    - https://github.com/suno-ai/bark
  description: |
    Bark is a transformer-based text-to-audio model created by Suno. Bark can generate highly realistic, multilingual speech as well as other audio - including music, background noise and simple sound effects. The model can also produce nonverbal communications like laughing, sighing and crying. To support the research community, we are providing access to pretrained model checkpoints, which are ready for inference and available for commercial use.
  tags:
    - text-to-speech
    - TTS
  license: MIT
  name: "cuda11-bark-development"
  uri: "quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-11-bark"
  alias: "bark"
  icon: https://avatars.githubusercontent.com/u/99442120?s=200&v=4
- !!merge <<: *bark
  name: "cuda12-bark-development"
  uri: "quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-12-bark"
- !!merge <<: *bark
  name: "rocm-bark-development"
  uri: "quay.io/go-skynet/local-ai-backends:master-gpu-rocm-hipblas-bark"
- !!merge <<: *bark
  name: "sycl-f32-bark"
  uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-intel-sycl-f32-bark"
- !!merge <<: *bark
  name: "sycl-f16-bark"
  uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-intel-sycl-f16-bark"
- !!merge <<: *bark
  name: "sycl-f32-bark-development"
  uri: "quay.io/go-skynet/local-ai-backends:master-gpu-intel-sycl-f32-bark"
- !!merge <<: *bark
  name: "sycl-f16-bark-development"
  uri: "quay.io/go-skynet/local-ai-backends:master-gpu-intel-sycl-f16-bark"
- &barkcpp
  urls:
    - https://github.com/PABannier/bark.cpp
  description: |
      With bark.cpp, our goal is to bring real-time realistic multilingual text-to-speech generation to the community.

      Plain C/C++ implementation without dependencies
      AVX, AVX2 and AVX512 for x86 architectures
      CPU and GPU compatible backends
      Mixed F16 / F32 precision
      4-bit, 5-bit and 8-bit integer quantization
      Metal and CUDA backends

      Models supported

          Bark Small
          Bark Large
  tags:
    - text-to-speech
    - TTS
  license: MIT
  icon: https://github.com/PABannier/bark.cpp/raw/main/assets/banner.png
  name: "bark-cpp"
  uri: "quay.io/go-skynet/local-ai-backends:latest-bark-cpp"
  alias: "bark-cpp"
- !!merge <<: *barkcpp
  name: "bark-cpp-development"
  uri: "quay.io/go-skynet/local-ai-backends:master-bark-cpp"
  alias: "bark-cpp"
## chatterbox
- &chatterbox
  urls:
    - https://github.com/resemble-ai/chatterbox
  description: |
    Resemble AI's first production-grade open source TTS model. Licensed under MIT, Chatterbox has been benchmarked against leading closed-source systems like ElevenLabs, and is consistently preferred in side-by-side evaluations.
    Whether you're working on memes, videos, games, or AI agents, Chatterbox brings your content to life. It's also the first open source TTS model to support emotion exaggeration control, a powerful feature that makes your voices stand out.
  tags:
    - text-to-speech
    - TTS
  license: MIT
  icon: https://private-user-images.githubusercontent.com/660224/448166653-bd8c5f03-e91d-4ee5-b680-57355da204d1.png?jwt=eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.eyJpc3MiOiJnaXRodWIuY29tIiwiYXVkIjoicmF3LmdpdGh1YnVzZXJjb250ZW50LmNvbSIsImtleSI6ImtleTUiLCJleHAiOjE3NTAxOTE0MDAsIm5iZiI6MTc1MDE5MTEwMCwicGF0aCI6Ii82NjAyMjQvNDQ4MTY2NjUzLWJkOGM1ZjAzLWU5MWQtNGVlNS1iNjgwLTU3MzU1ZGEyMDRkMS5wbmc_WC1BbXotQWxnb3JpdGhtPUFXUzQtSE1BQy1TSEEyNTYmWC1BbXotQ3JlZGVudGlhbD1BS0lBVkNPRFlMU0E1M1BRSzRaQSUyRjIwMjUwNjE3JTJGdXMtZWFzdC0xJTJGczMlMkZhd3M0X3JlcXVlc3QmWC1BbXotRGF0ZT0yMDI1MDYxN1QyMDExNDBaJlgtQW16LUV4cGlyZXM9MzAwJlgtQW16LVNpZ25hdHVyZT1hMmI1NGY3OGFiZTlhNGFkNTVlYTY4NTIwMWEzODRiZGE4YzdhNGQ5MGNhNzE3MDYyYTA2NDIxYTkyYzhiODkwJlgtQW16LVNpZ25lZEhlYWRlcnM9aG9zdCJ9.mR9kM9xX0TdzPuSpuspCllHYQiq79dFQ2rtuNvjrl6w
  name: "cuda11-chatterbox-development"
  uri: "quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-11-chatterbox"
  alias: "chatterbox"
- !!merge <<: *chatterbox
  name: "cuda12-chatterbox-development"
  uri: "quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-12-chatterbox"
- !!merge <<: *chatterbox
  name: "cuda11-chatterbox"
  uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-11-chatterbox"
- !!merge <<: *chatterbox
  name: "cuda12-chatterbox"
  uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-12-chatterbox"