Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Code sync for upstream v0.14.0 #421

Merged
merged 95 commits into from
Oct 28, 2024
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
95 commits
Select commit Hold shift + click to select a range
56a4e7d
Propagate `trust_remote_code` flag throughout vLLM startup (#3729)
calwoo Jun 21, 2024
352e030
Fix dead links on PyPI (#3754)
kevinbazira Jun 24, 2024
d19e310
Fix model is ready even if there is no model (#3275)
HAO2167 Jun 24, 2024
fbd8778
Fix No model ready error in multi model serving (#3758)
sivanantha321 Jun 27, 2024
74c9ff4
Initial implementation of Inference client (#3401)
sivanantha321 Jun 29, 2024
d4349ea
Fix logprobs for vLLM (#3738)
sivanantha321 Jun 29, 2024
68b04ef
Fix model name not properly parsed by inference graph (#3746)
sivanantha321 Jun 29, 2024
ca691f7
pillow - Buffer Overflow (#3598)
spolti Jun 29, 2024
164ea83
Use add_generation_prompt while creating chat template (#3775)
Datta0 Jul 11, 2024
1a70e11
Deduplicate the names for the additional domain names (#3773)
houshengbo Jul 12, 2024
29731be
Make Virtual Service case-insensitive (#3779)
andyi2it Jul 15, 2024
580a0f3
Install packages needed for vllm model load (#3802)
gavrissh Jul 18, 2024
31d2395
Make gRPC max message length configurable (#3741)
sivanantha321 Jul 20, 2024
5736731
Add readiness probe for MLServer and Increase memory for pmml in CI (…
sivanantha321 Jul 20, 2024
bb9641f
Several bug fixes for vLLM completion endpoint (#3788)
sivanantha321 Jul 21, 2024
de96bd3
Increase timeout to make unit test stable (#3808)
Jooho Jul 25, 2024
32d3fc0
Upgrade CI deps (#3822)
sivanantha321 Jul 27, 2024
3862175
Add tests for vLLM (#3771)
sivanantha321 Jul 27, 2024
f9e7d5a
Bump python to 3.11 for serving runtime images and Bump poetry to 1.8…
sivanantha321 Jul 27, 2024
96fb00e
Bump vLLM to 0.5.3.post1 (#3828)
sivanantha321 Aug 2, 2024
c080da5
Refactor the ModelServer to let uvicorn handle multiple workers and u…
sivanantha321 Aug 6, 2024
d73f1ca
Update golang for docs/Dockerfile to 1.21 (#3761)
spolti Aug 10, 2024
9632a52
Make ray an optional dependency (#3834)
sivanantha321 Aug 11, 2024
a6a061e
Update aif example (#3765)
spolti Aug 11, 2024
f9c73c2
Use helm for quick installation (#3813)
sivanantha321 Aug 12, 2024
2fae6e2
Allow KServe to have its own local gateways for Serverless mode (#3737)
israel-hdez Aug 17, 2024
61b5e7e
Add support for Azure DNS zone endpoints (#3819)
tjandy98 Aug 17, 2024
a16f2d7
Fix failed build for knativeLocalGatewayService (#3866)
yuzisun Aug 18, 2024
9292c88
Add logging request feature for vLLM backend (#3849)
sivanantha321 Aug 19, 2024
656f65e
Bump vLLM to 0.5.4 (#3874)
sivanantha321 Aug 21, 2024
99fa478
Fix: Add workaround for snyk image scan failure (#3880)
sivanantha321 Aug 21, 2024
87cf2cd
Fix trust_remote_code not working with huggingface backend (#3879)
sivanantha321 Aug 21, 2024
e82beb6
Update KServe 2024-2025 Roadmap (#3810)
yuzisun Aug 21, 2024
c10f548
Configurable image pull secrets in Helm charts (#3838)
saileshd1402 Aug 24, 2024
7dd4ae2
Fix issue with rolling update behavior (#3786)
andyi2it Aug 24, 2024
b89c8c2
Fix the 'tokens exceeding model limit' error response in vllm server …
saileshd1402 Aug 24, 2024
69cdca5
Add support for binary data extension protocol and FP16 datatype (#3685)
sivanantha321 Aug 24, 2024
0a6302b
Protobuf version upgrade 4.25.4 (#3881)
andyi2it Aug 24, 2024
a9e967f
Adds optional labels and annotations to the controller (#3366)
guitouni Aug 24, 2024
f17d068
Enable Server-Side Apply for Kustomize Overlays in Test Environment (…
Jooho Aug 24, 2024
6978ab9
bufix: update image_transformer.py to handle changes in input structu…
zwong91 Aug 24, 2024
b7431e2
support text embedding task in hugging face server (#3743)
kevinmingtarja Aug 24, 2024
1bd82fb
Rename max_length parameter to max_model_len to be in sync with vLLM …
Datta0 Aug 25, 2024
74591b4
[Upstream] - Update-istio version based on go version 1.21 (#3825)
mholder6 Aug 25, 2024
9bca4ba
Enrich isvc NotReady events for failed conditions (#3303)
asdqwe123zxc Aug 26, 2024
c05d760
adding metadata on requests (#3635)
gcemaj Aug 26, 2024
ab251d6
Publish 0.14.0-rc0 release (#3867)
yuzisun Aug 27, 2024
ddc56ca
Use API token for publishing package to PyPI (#3896)
sivanantha321 Aug 28, 2024
d2f90dc
Fix sdlc broken when kserve installed using helm (#3890)
sivanantha321 Aug 28, 2024
3a347c5
Add Security Context and Resources to RBAC Proxy (#3898)
HotsauceLee Aug 28, 2024
e879a39
Remove unwanted cluster scope secret permissions (#3893)
sivanantha321 Aug 30, 2024
67373ad
bump to vllm 0.5.5 (#3911)
lizzzcai Sep 3, 2024
c80dae9
pin gosec to 2.20.0 (#3921)
greenmoon55 Sep 5, 2024
c7e99d8
add a new doc 'common issues and solutions' (#3878)
Jooho Sep 7, 2024
305d393
Implement health endpoint for vLLM backend (#3850)
sivanantha321 Sep 7, 2024
f54e27a
Add security best practices for inferenceservice, inferencegraph, ser…
sivanantha321 Sep 7, 2024
e7353d1
Bump Go to 1.22 (#3912)
sivanantha321 Sep 11, 2024
d779344
bump to vllm 0.6.0 (#3934)
hustxiayang Sep 13, 2024
fef6c7a
Set the volume mount's readonly annotation based on the ISVC annotati…
hdefazio Sep 15, 2024
391c8c6
mount /dev/shm volume to huggingfaceserver (#3910)
lizzzcai Sep 16, 2024
9ec6842
Fix permission error in snyk scan (#3889)
sivanantha321 Sep 16, 2024
acfc887
Cluster Local Model CR (#3839)
greenmoon55 Sep 17, 2024
90a5e12
added http headers to inbound request (#3895)
andyi2it Sep 17, 2024
a2f612c
Add prow-github-action (#3888)
sivanantha321 Sep 19, 2024
02293ac
Add TLS support for Inference Loggers (#3863)
ruivieira Sep 19, 2024
536fc9b
Fix explainer endpoint not working with path based routing (#3257)
sivanantha321 Sep 19, 2024
d97baa6
Fix ingress configuration for path based routing and update go mod (…
sivanantha321 Sep 19, 2024
a0a4d00
Add HostIPC field to ServingRuntimePodSpec (#3943)
greenmoon55 Sep 23, 2024
bf6fae8
remove conversion wehbook part from self-signed-ca.sh (#3941)
Jooho Sep 23, 2024
2376eeb
update fluid kserve sample to use huggingface servingruntime (#3907)
lizzzcai Sep 23, 2024
80982c2
bump to vLLM0.6.1post2 (#3948)
hustxiayang Sep 24, 2024
12c4039
Add NodeDownloadPending status to ClusterLocalModel (#3955)
greenmoon55 Sep 26, 2024
9380e99
add tags to rest server timing logs to differentiate cpu and wall tim…
gfkeith Sep 27, 2024
1e28d4f
Implement Huggingface model download in storage initializer (#3584)
andyi2it Sep 29, 2024
b344a0a
Update OWNERS file (#3966)
yuzisun Sep 30, 2024
20b6e29
Cluster local model controller (#3860)
greenmoon55 Oct 2, 2024
a50fdc9
Prepare for 0.14.0-rc1release and automate sync process (#3970)
sivanantha321 Oct 3, 2024
d5ed018
add a new API for multi-node/multi-gpu (#3871)
Jooho Oct 3, 2024
ecc3729
Fix update-openapigen.sh that can be executed from kserve dir (#3924)
Jooho Oct 5, 2024
24d882b
Add python 3.12 support and remove python 3.8 support (#3645)
sivanantha321 Oct 6, 2024
17725be
Fix openssl vulnerability CWE-1395 (#3975)
sivanantha321 Oct 9, 2024
d7d79e1
Fix Kubernetes Doc Links (#3670)
jyono Oct 9, 2024
70e12ff
Fix kserve local testing env (#3981)
yuzisun Oct 9, 2024
dec8c14
Fix streaming response not working properly with logger (#3847)
sivanantha321 Oct 10, 2024
6ff2a2f
Add a flag for automount serviceaccount token (#3979)
greenmoon55 Oct 10, 2024
d2695a5
Do not set security context on the storage initializer from user cont…
greenmoon55 Oct 11, 2024
7796c44
Modelcar race condition mitigation with an init container (#3932)
israel-hdez Oct 11, 2024
fc72a2b
Fix: Headers passing for v1/v2 endpoints (#3669)
andyi2it Oct 12, 2024
dbceef3
Torchserve security update (#3774)
udaij12 Oct 14, 2024
82234c0
Pin ubuntu 22.04 for minikube setup action (#3994)
greenmoon55 Oct 14, 2024
7e43642
KServe 0.14 Release (#3988)
greenmoon55 Oct 14, 2024
befa4d6
Merge remote-tracking branch 'kserve/release-0.14' into j9436-kserve0…
israel-hdez Oct 22, 2024
53de246
Fix poetry lockfiles after v0.14.0 code sync
israel-hdez Oct 24, 2024
b7a868f
Restore compatibility with go v1.21
israel-hdez Oct 24, 2024
c9453bf
Merge branch 'odh-master' into j9436-kserve014-upgrade
israel-hdez Oct 28, 2024
File filter

Filter by extension

Filter by extension


Conversations
Failed to load comments.
Loading
Jump to
The table of contents is too big for display.
Diff view
Diff view
  •  
  •  
  •  
8 changes: 3 additions & 5 deletions .github/actions/minikube-setup/action.yml
Original file line number Diff line number Diff line change
Expand Up @@ -7,16 +7,14 @@ runs:
- name: Install kubectl
uses: azure/setup-kubectl@v4.0.0
with:
version: 'v1.27.4'
version: 'v1.29.7'

- name: Setup Minikube
uses: medyagh/setup-minikube@latest
with:
minikube-version: '1.32.0'
kubernetes-version: 'v1.27.4'
minikube-version: '1.33.1'
kubernetes-version: 'v1.29.7'
driver: 'none'
network-plugin: 'cni'
cni: 'calico'
wait: 'all'
start-args: --wait-timeout=6m0s

Expand Down
31 changes: 31 additions & 0 deletions .github/labels.yaml
Original file line number Diff line number Diff line change
@@ -0,0 +1,31 @@
# Labels for labeling issues and pull requests using GitHub prow action.
kind:
- 'bug'
- 'discussion'
- 'feature'
- 'process'
- 'question'

area:
- 'api'
- 'azure'
- 'docs'
- 'example'
- 'gcp'
- 'inference'
- 'infrastructure-feature'
- 'logging'
- 'operator'
- 'performance'
- 'testing'
- 'project-health'
- 'servingruntime'
- 'inferencegraph'
- 'storage'
- 'inferenceservice'
- 'control-plane'

priority:
- 'p0'
- 'p1'
- 'p2'
2 changes: 1 addition & 1 deletion .github/workflows/automated-release.yml
Original file line number Diff line number Diff line change
Expand Up @@ -16,7 +16,7 @@ jobs:
- name: Setup Go
uses: actions/setup-go@v5
with:
go-version: 1.21
go-version: 1.22

- name: Checkout source code
uses: actions/checkout@v4
Expand Down
62 changes: 43 additions & 19 deletions .github/workflows/e2e-test.yml
Original file line number Diff line number Diff line change
Expand Up @@ -23,6 +23,7 @@ env:
BASE_ARTIFACT_PREFIX: "base"
# Controller images
CONTROLLER_IMG: "kserve-controller"
LOCALMODEL_CONTROLLER_IMG: "kserve-localmodel-controller"
STORAGE_INIT_IMG: "storage-initializer"
AGENT_IMG: "agent"
ROUTER_IMG: "router"
Expand Down Expand Up @@ -55,6 +56,9 @@ jobs:
- name: Checkout source
uses: actions/checkout@v4

- name: Free-up disk space
uses: ./.github/actions/free-up-disk-space

- name: Setup Docker Buildx
uses: docker/setup-buildx-action@v3

Expand All @@ -73,6 +77,14 @@ jobs:
path: ${{ env.DOCKER_IMAGES_PATH }}/${{ env.CONTROLLER_IMG }}-${{ github.sha }}
compression-level: 0
if-no-files-found: error

- name: Upload localmodel controller image
uses: actions/upload-artifact@v4
with:
name: ${{ env.BASE_ARTIFACT_PREFIX }}-${{ env.LOCALMODEL_CONTROLLER_IMG }}-${{ github.sha }}
path: ${{ env.DOCKER_IMAGES_PATH }}/${{ env.LOCALMODEL_CONTROLLER_IMG }}-${{ github.sha }}
compression-level: 0
if-no-files-found: error

- name: Upload agent image
uses: actions/upload-artifact@v4
Expand Down Expand Up @@ -272,7 +284,7 @@ jobs:
if-no-files-found: error

test-predictor:
runs-on: ubuntu-latest
runs-on: ubuntu-22.04
needs:
[
kserve-image-build,
Expand All @@ -288,7 +300,7 @@ jobs:
- name: Setup Go
uses: actions/setup-go@v5
with:
go-version: "1.21"
go-version: "1.22"

- name: Setup Python
uses: actions/setup-python@v5
Expand Down Expand Up @@ -337,7 +349,7 @@ jobs:
./test/scripts/gh-actions/status-check.sh

test-transformer-explainer-mms:
runs-on: ubuntu-latest
runs-on: ubuntu-22.04
needs:
[kserve-image-build, predictor-runtime-build, explainer-runtime-build]
steps:
Expand All @@ -350,7 +362,8 @@ jobs:
- name: Setup Go
uses: actions/setup-go@v5
with:
go-version: "1.21"
go-version: "1.22"

- name: Setup Python
uses: actions/setup-python@v5
with:
Expand Down Expand Up @@ -416,7 +429,7 @@ jobs:
./test/scripts/gh-actions/status-check.sh

test-graph:
runs-on: ubuntu-latest
runs-on: ubuntu-22.04
needs:
[
kserve-image-build,
Expand All @@ -430,7 +443,7 @@ jobs:
- name: Setup Go
uses: actions/setup-go@v5
with:
go-version: "1.21"
go-version: "1.22"

- name: Setup Python
uses: actions/setup-python@v5
Expand Down Expand Up @@ -495,7 +508,7 @@ jobs:


test-path-based-routing:
runs-on: ubuntu-latest
runs-on: ubuntu-22.04
needs:
[
kserve-image-build,
Expand All @@ -508,7 +521,7 @@ jobs:
- name: Setup Go
uses: actions/setup-go@v5
with:
go-version: "1.21"
go-version: "1.22"

- name: Setup Python
uses: actions/setup-python@v5
Expand Down Expand Up @@ -551,6 +564,12 @@ jobs:
name: ${{ env.TRANSFORMER_ARTIFACT_PREFIX }}-${{ env.IMAGE_TRANSFORMER_IMG }}-${{ github.sha }}
path: ./tmp

- name: Download Art Explainer image
uses: actions/download-artifact@v4
with:
name: ${{ env.EXPLAINER_ARTIFACT_PREFIX }}-${{ env.ART_IMG }}-${{ github.sha }}
path: ./tmp

- name: Load docker images
uses: ./.github/actions/load-docker-images
with:
Expand Down Expand Up @@ -582,7 +601,7 @@ jobs:
./test/scripts/gh-actions/status-check.sh

test-qpext:
runs-on: ubuntu-latest
runs-on: ubuntu-22.04
needs: [kserve-image-build, predictor-runtime-build]
steps:
- name: Checkout source
Expand All @@ -594,7 +613,7 @@ jobs:
- name: Setup Go
uses: actions/setup-go@v5
with:
go-version: "1.21"
go-version: "1.22"
- name: Setup Python
uses: actions/setup-python@v5
with:
Expand Down Expand Up @@ -647,22 +666,26 @@ jobs:
./test/scripts/gh-actions/status-check.sh

test-with-helm:
runs-on: ubuntu-latest
runs-on: ubuntu-22.04
needs:
[kserve-image-build]
steps:
- name: Checkout source
uses: actions/checkout@v4

- name: Setup Go
uses: actions/setup-go@v5
with:
go-version: "1.21"
go-version: "1.22"

- name: Setup Python
uses: actions/setup-python@v5
with:
python-version: "3.9"

- uses: ./.github/actions/free-up-disk-space
- name: Free-up disk space
uses: ./.github/actions/free-up-disk-space

- name: Setup Minikube
uses: ./.github/actions/minikube-setup

Expand Down Expand Up @@ -694,7 +717,7 @@ jobs:
./test/scripts/gh-actions/status-check.sh

test-raw:
runs-on: ubuntu-latest
runs-on: ubuntu-22.04
needs:
[kserve-image-build, predictor-runtime-build]
steps:
Expand All @@ -707,7 +730,7 @@ jobs:
- name: Setup Go
uses: actions/setup-go@v5
with:
go-version: "1.21"
go-version: "1.22"
- name: Setup Python
uses: actions/setup-python@v5
with:
Expand Down Expand Up @@ -774,7 +797,7 @@ jobs:
./test/scripts/gh-actions/status-check.sh

test-kourier:
runs-on: ubuntu-latest
runs-on: ubuntu-22.04
needs:
[kserve-image-build, predictor-runtime-build, graph-tests-images-build]
steps:
Expand All @@ -787,7 +810,8 @@ jobs:
- name: Setup Go
uses: actions/setup-go@v5
with:
go-version: "1.21"
go-version: "1.22"

- name: Setup Python
uses: actions/setup-python@v5
with:
Expand Down Expand Up @@ -858,7 +882,7 @@ jobs:
./test/scripts/gh-actions/status-check.sh "kourier"

test-llm:
runs-on: ubuntu-latest
runs-on: ubuntu-22.04
needs:
[ kserve-image-build, predictor-runtime-build]
steps:
Expand All @@ -871,7 +895,7 @@ jobs:
- name: Setup Go
uses: actions/setup-go@v5
with:
go-version: "1.21"
go-version: "1.22"
- name: Setup Python
uses: actions/setup-python@v5
with:
Expand Down
2 changes: 1 addition & 1 deletion .github/workflows/go.yml
Original file line number Diff line number Diff line change
Expand Up @@ -19,7 +19,7 @@ jobs:
- name: Set up Go 1.x
uses: actions/setup-go@v5
with:
go-version: "1.21"
go-version: "1.22"
id: go

- name: Check out code into the Go module directory
Expand Down
2 changes: 1 addition & 1 deletion .github/workflows/golangci-lint.yml
Original file line number Diff line number Diff line change
Expand Up @@ -18,7 +18,7 @@ jobs:
- uses: actions/checkout@v4
- uses: actions/setup-go@v5
with:
go-version: '1.21'
go-version: '1.22'
cache: false
- name: golangci-lint
uses: golangci/golangci-lint-action@v4
Expand Down
95 changes: 95 additions & 0 deletions .github/workflows/kserve-localmodel-controller-docker-publish.yml
Original file line number Diff line number Diff line change
@@ -0,0 +1,95 @@
name: Kserve localmodel controller Docker Publisher

on:
push:
# Publish `master` as Docker `latest` image.
branches:
- master

# Publish `v1.2.3` tags as releases.
tags:
- v*

# Run tests for any PRs.
pull_request:

env:
IMAGE_NAME: kserve-localmodel-controller

concurrency:
group: ${{ github.workflow }}-${{ github.ref }}
cancel-in-progress: true

jobs:
# Run tests.
# See also https://docs.docker.com/docker-hub/builds/automated-testing/
test:
runs-on: ubuntu-latest

steps:
- name: Checkout source
uses: actions/checkout@v4

- name: Run tests
run: |
if [ -f docker-compose.test.yml ]; then
docker-compose --file docker-compose.test.yml build
docker-compose --file docker-compose.test.yml run sut
else
docker buildx build . --file localmodel.Dockerfile
fi

# Push image to GitHub Packages.
# See also https://docs.docker.com/docker-hub/builds/
push:
# Ensure test job passes before pushing image.
needs: test

runs-on: ubuntu-latest
if: github.event_name == 'push'

steps:
- name: Checkout source
uses: actions/checkout@v4

- name: Setup QEMU
uses: docker/setup-qemu-action@v3

- name: Setup Docker Buildx
uses: docker/setup-buildx-action@v3

- name: Login to DockerHub
uses: docker/login-action@v3
with:
username: ${{ secrets.DOCKER_USER }}
password: ${{ secrets.DOCKER_PASSWORD }}

- name: export version variable
run: |
IMAGE_ID=kserve/$IMAGE_NAME

# Change all uppercase to lowercase
IMAGE_ID=$(echo $IMAGE_ID | tr '[A-Z]' '[a-z]')

# Strip git ref prefix from version
VERSION=$(echo "${{ github.ref }}" | sed -e 's,.*/\(.*\),\1,')

# Strip "v" prefix from tag name
# [[ "${{ github.ref }}" == "refs/tags/"* ]] && VERSION=$(echo $VERSION | sed -e 's/^v//')

# Use Docker `latest` tag convention
[ "$VERSION" == "master" ] && VERSION=latest

echo VERSION=$VERSION >> $GITHUB_ENV
echo IMAGE_ID=$IMAGE_ID >> $GITHUB_ENV

- name: Build and push
uses: docker/build-push-action@v5
with:
platforms: linux/amd64,linux/arm/v7,linux/arm64/v8,linux/ppc64le,linux/s390x
context: .
file: localmodel.Dockerfile
push: true
tags: ${{ env.IMAGE_ID }}:${{ env.VERSION }}
# https://github.com/docker/buildx/issues/1533
provenance: false
Loading
Loading