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-master"
  uri: "quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-11-vllm"
- !!merge <<: *vllm
  name: "cuda12-vllm-master"
  uri: "quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-12-vllm"
- !!merge <<: *vllm
  name: "rocm-vllm-master"
  uri: "quay.io/go-skynet/local-ai-backends:master-gpu-rocm-hipblas-vllm"
- !!merge <<: *vllm
  name: "intel-sycl-f32-vllm-master"
  uri: "quay.io/go-skynet/local-ai-backends:master-gpu-intel-sycl-f32-vllm"
- !!merge <<: *vllm
  name: "intel-sycl-f16-vllm-master"
  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-master"
  uri: "quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-11-rerankers"
  alias: "rerankers"

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

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

- name: "intel-sycl-f16-rerankers-master"
  uri: "quay.io/go-skynet/local-ai-backends:master-gpu-intel-sycl-f16-rerankers"
  alias: "rerankers"
## Transformers
- name: "cuda12-transformers"
  uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-12-transformers"
  alias: "cuda12-transformers"
- name: "rocm-transformers"
  uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-rocm-hipblas-transformers"
  alias: "rocm-transformers"
- name: "intel-sycl-f32-transformers"
  uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-intel-sycl-f32-transformers"
  alias: "intel-sycl-f32-transformers"

- name: "intel-sycl-f16-transformers"
  uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-intel-sycl-f16-transformers"
  alias: "intel-sycl-f16-transformers"
- name: "cuda11-transformers-master"
  uri: "quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-11-transformers"
  alias: "transformers"
- name: "cuda11-transformers"
  uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-11-transformers"
  alias: "cuda11-transformers"


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


- name: "rocm-transformers-master"
  uri: "quay.io/go-skynet/local-ai-backends:master-gpu-rocm-hipblas-transformers"
  alias: "transformers"



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

- name: "intel-sycl-f16-transformers-master"
  uri: "quay.io/go-skynet/local-ai-backends:master-gpu-intel-sycl-f16-transformers"
  alias: "transformers"
## Diffusers
- name: "cuda12-diffusers"
  uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-12-diffusers"
  alias: "cuda12-diffusers"
- name: "rocm-diffusers"
  uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-rocm-hipblas-diffusers"
  alias: "rocm-diffusers"
- name: "cuda11-diffusers"
  uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-11-diffusers"
  alias: "cuda11-diffusers"


- name: "intel-sycl-f32-diffusers"
  uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-intel-sycl-f32-diffusers"
  alias: "intel-sycl-f32-diffusers"

- name: "cuda11-diffusers-master"
  uri: "quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-11-diffusers"
  alias: "diffusers"

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

- name: "rocm-diffusers-master"
  uri: "quay.io/go-skynet/local-ai-backends:master-gpu-rocm-hipblas-diffusers"
  alias: "diffusers"

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

  ## exllama2
- name: "cuda11-exllama2"
  uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-11-exllama2"
  alias: "cuda11-exllama2"
- name: "cuda12-exllama2"
  uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-12-exllama2"
  alias: "cuda12-exllama2"

- name: "cuda11-exllama2-master"
  uri: "quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-11-exllama2"
  alias: "exllama2"


- name: "cuda12-exllama2-master"
  uri: "quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-12-exllama2"
  alias: "exllama2"

## kokoro
- name: "cuda11-kokoro-master"
  uri: "quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-11-kokoro"
  alias: "kokoro"

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

- name: "rocm-kokoro-master"
  uri: "quay.io/go-skynet/local-ai-backends:master-gpu-rocm-hipblas-kokoro"
  alias: "kokoro"

- name: "sycl-f32-kokoro"
  uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-intel-sycl-f32-kokoro"
  alias: "kokoro"

- name: "sycl-f16-kokoro"
  uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-intel-sycl-f16-kokoro"
  alias: "kokoro"

- name: "sycl-f16-kokoro-master"
  uri: "quay.io/go-skynet/local-ai-backends:master-gpu-intel-sycl-f16-kokoro"
  alias: "kokoro"

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

## faster-whisper
- name: "cuda11-faster-whisper-master"
  uri: "quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-11-faster-whisper"
  alias: "faster-whisper"

- name: "cuda12-faster-whisper-master"
  uri: "quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-12-faster-whisper"
  alias: "faster-whisper"

- name: "rocm-faster-whisper-master"
  uri: "quay.io/go-skynet/local-ai-backends:master-gpu-rocm-hipblas-faster-whisper"
  alias: "faster-whisper"

- name: "sycl-f32-faster-whisper"
  uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-intel-sycl-f32-faster-whisper"
  alias: "faster-whisper"

- name: "sycl-f16-faster-whisper"
  uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-intel-sycl-f16-faster-whisper"
  alias: "faster-whisper"

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

- name: "sycl-f16-faster-whisper-master"
  uri: "quay.io/go-skynet/local-ai-backends:master-gpu-intel-sycl-f16-faster-whisper"
  alias: "faster-whisper"

## coqui

- name: "cuda11-coqui-master"
  uri: "quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-11-coqui"
  alias: "coqui"

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

- name: "rocm-coqui-master"
  uri: "quay.io/go-skynet/local-ai-backends:master-gpu-rocm-hipblas-coqui"
  alias: "coqui"

- name: "sycl-f32-coqui"
  uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-intel-sycl-f32-coqui"
  alias: "coqui"

- name: "sycl-f16-coqui"
  uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-intel-sycl-f16-coqui"
  alias: "coqui"

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

- name: "sycl-f16-coqui-master"
  uri: "quay.io/go-skynet/local-ai-backends:master-gpu-intel-sycl-f16-coqui"
  alias: "coqui"

## bark
- name: "cuda11-bark-master"
  uri: "quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-11-bark"
  alias: "bark"

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

- name: "rocm-bark-master"
  uri: "quay.io/go-skynet/local-ai-backends:master-gpu-rocm-hipblas-bark"
  alias: "bark"

- name: "sycl-f32-bark"
  uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-intel-sycl-f32-bark"
  alias: "bark"

- name: "sycl-f16-bark"
  uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-intel-sycl-f16-bark"
  alias: "bark"

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

- name: "sycl-f16-bark-master"
  uri: "quay.io/go-skynet/local-ai-backends:master-gpu-intel-sycl-f16-bark"
  alias: "bark"

## chatterbox

- name: "cuda11-chatterbox-master"
  uri: "quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-11-chatterbox"
  alias: "chatterbox"

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

- name: "cuda11-chatterbox"
  uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-11-chatterbox"
  alias: "chatterbox"

- name: "cuda12-chatterbox"
  uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-12-chatterbox"
  alias: "chatterbox"