chore: drop vllm for cuda 11 (#5881)

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

.github/workflows/backend.yml

@@ -63,18 +63,6 @@ jobs:
             backend: "llama-cpp"
             dockerfile: "./backend/Dockerfile.llama-cpp"
             context: "./"
-          - build-type: 'cublas'
-            cuda-major-version: "11"
-            cuda-minor-version: "7"
-            platforms: 'linux/amd64'
-            tag-latest: 'auto'
-            tag-suffix: '-gpu-nvidia-cuda-11-vllm'
-            runs-on: 'ubuntu-latest'
-            base-image: "ubuntu:22.04"
-            skip-drivers: 'false'
-            backend: "vllm"
-            dockerfile: "./backend/Dockerfile.python"
-            context: "./backend"
           - build-type: 'cublas'
             cuda-major-version: "11"
             cuda-minor-version: "7"

backend/index.yaml

@@ -502,9 +502,6 @@
     nvidia: "cuda12-vllm-development"
     amd: "rocm-vllm-development"
     intel: "intel-sycl-f16-vllm-development"
-- !!merge <<: *vllm
-  name: "cuda11-vllm"
-  uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-11-vllm"
 - !!merge <<: *vllm
   name: "cuda12-vllm"
   uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-12-vllm"
@@ -517,9 +514,6 @@
 - !!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"