Fix docker upload bugs

.github/actions/nm-get-docker-tags/action.yml

@@ -4,8 +4,8 @@ inputs:
   wf_category:
     description: "type of nm-vllm to install for the docker image: NIGHTLY or RELEASE"
     required: true
-  wheel:
-    description: "wheel name, if latest use the latest from nm pypi"
+  whl:
+    description: "name of nm-vllm wheel to install for the docker image"
     required: true
 outputs:
   tag:
@@ -22,16 +22,23 @@ runs:
   steps:
   - id: tags
     run: |
-      BUILD_VERSION=`echo "${{ inputs.wheel }}" | cut -d'-' -f2`
+      BUILD_VERSION=`echo "${{ inputs.whl }}" | cut -d'-' -f2`
       if [[ "${{ inputs.wf_category }}" == "RELEASE" ]]; then
-          TAG="v${build_version}"
-          EXTRA_TAG=latest
+          if [[ "${BUILD_VERSION}" =~ ^[0-9]+.[0-9]+.[0-9]+$ ]]; then
+              TAG="v${BUILD_VERSION}"
+              EXTRA_TAG=latest
+          else
+              echo "ERROR: wheel version ${BUILD_VERSION} doesn't match RELEASE format. Check input."
+              exit 1
+          fi
       else
-          TAG=`echo "${build_version}" | cut -d'.' -f4`
-          EXTRA_TAG=nightly
-      fi
-      if [[ "${{ inputs.wheel }}" == "latest" ]]; then
-          BUILD_VERSION="latest"
+          if [[ "${BUILD_VERSION}" =~ ^[0-9]+.[0-9]+.[0-9]+.[0-9]{8}$ ]]; then
+              TAG=`echo "${BUILD_VERSION}" | cut -d'.' -f4`
+              EXTRA_TAG=nightly
+          else
+              echo "ERROR: wheel version ${BUILD_VERSION} doesn't match NIGHTLY format. Check input."
+              exit 1
+          fi
       fi
       echo "tag=${TAG}" >> $GITHUB_OUTPUT
       echo "extra_tag=${EXTRA_TAG}" >> $GITHUB_OUTPUT

.github/workflows/nm-build-test.yml

@@ -173,12 +173,12 @@ jobs:
 
     # update docker
     DOCKER:
-        needs: [BUILD, UPLOAD]
-        if: ${{ inputs.push_to_pypi }}
+        needs: [BUILD]
+        if: ${{ inputs.wf_category != 'REMOTE' }}
         uses: ./.github/workflows/publish-docker.yml
         with:
             push_to_repository: ${{ inputs.push_to_pypi }}
             gitref: ${{ inputs.gitref }}
             wf_category: ${{ inputs.wf_category }}
-            wheel: ${{ needs.BUILD.outputs.whl }}
+            whl: ${{ needs.BUILD.outputs.whl }}
         secrets: inherit

.github/workflows/nm-build.yml

@@ -31,6 +31,10 @@ on:
         description: "python version, e.g. 3.10.12"
         type: string
         required: true
+    outputs:
+      whl:
+        description: 'basename for generated whl'
+        value: ${{ jobs.BUILD.outputs.whl }}
 
   # makes workflow manually callable
   workflow_dispatch:

.github/workflows/publish-docker.yml

@@ -15,10 +15,10 @@ on:
         description: "type of nm-vllm to install for the docker image: NIGHTLY (default) or RELEASE"
         type: string
         default: 'NIGHTLY'
-      wheel:
-        description: "nm-vllm wheel to install for the docker image: latest (default) or specific wheel name"
+      whl:
+        description: "nm-vllm wheel to install for the docker image"
         type: string
-        default: 'latest'
+        required: true
 
   workflow_dispatch:
     inputs:
@@ -34,10 +34,10 @@ on:
         description: "type of nm-vllm to install for the docker image: NIGHTLY (default) or RELEASE"
         type: string
         default: 'NIGHTLY'
-      wheel:
-        description: "nm-vllm wheel to install for the docker image: latest (default) or specific wheel name"
+      whl:
+        description: "nm-vllm wheel to install for the docker image"
         type: string
-        default: 'latest'
+        required: true
 
 jobs:
     build-docker-image:
@@ -70,7 +70,7 @@ jobs:
             uses: ./.github/actions/nm-get-docker-tags/
             with:
               wf_category: ${{ inputs.wf_category }}
-              wheel: ${{ inputs.wheel }}
+              whl: ${{ inputs.whl }}
 
           - name: Build image
             id: build

Dockerfile

@@ -62,20 +62,6 @@ RUN apt-get update -y && apt-get install -y ccache
 
 #################### EXTENSION Build IMAGE ####################
 
-#################### FLASH_ATTENTION Build IMAGE ####################
-FROM dev as flash-attn-builder
-# flash attention version
-ARG flash_attn_version=v2.5.8
-ENV FLASH_ATTN_VERSION=${flash_attn_version}
-
-WORKDIR /usr/src/flash-attention-v2
-
-# Download the wheel or build it if a pre-compiled release doesn't exist
-RUN pip --verbose wheel flash-attn==${FLASH_ATTN_VERSION} \
-    --no-build-isolation --no-deps --no-cache-dir
-
-#################### FLASH_ATTENTION Build IMAGE ####################
-
 #################### vLLM installation IMAGE ####################
 # image with vLLM installed
 FROM nvidia/cuda:${CUDA_VERSION}-base-ubuntu22.04 AS vllm-base
@@ -114,9 +100,6 @@ RUN --mount=type=bind,from=build \
         fi; \
     fi
 
-RUN --mount=type=bind,from=flash-attn-builder,src=/usr/src/flash-attention-v2,target=/usr/src/flash-attention-v2 \
-    --mount=type=cache,target=/root/.cache/pip \
-    pip install /usr/src/flash-attention-v2/*.whl --no-cache-dir
 #################### vLLM installation IMAGE ####################
 
 #################### TEST IMAGE ####################