kserve/kserve issues and pull requests

#3842 - Update OPENSHIFT_GUIDE.md

Pull Request - State: open - Opened by ksdeekshith 3 months ago

#3841 - Creating the InferenceService with gRPC (tensorflow serving apis missing imports)

Issue - State: open - Opened by LOADBC 3 months ago

#3840 - Support Image tasks in huggingface server

Issue - State: open - Opened by oplushappy 3 months ago - 1 comment
Labels: kserve/llm

#3839 - Cluster Local Model CR

Pull Request - State: closed - Opened by greenmoon55 3 months ago - 5 comments
Labels: lgtm, approved

#3838 - Configurable image pull secrets in Helm charts

Pull Request - State: closed - Opened by saileshd1402 4 months ago - 2 comments
Labels: lgtm, approved

#3837 - Support for TLS enabled logger endpoints

Issue - State: closed - Opened by ruivieira 4 months ago - 1 comment

#3836 - Support multiple inference loggers

Issue - State: open - Opened by ruivieira 4 months ago - 3 comments
Labels: kfserving/logger

#3834 - Make ray an optional dependency

Pull Request - State: closed - Opened by sivanantha321 4 months ago - 4 comments
Labels: lgtm, approved

#3832 - How can I login with an API key when serving a Hugging Face model?

Issue - State: closed - Opened by rlatjswlr123 4 months ago - 4 comments

#3831 - Different knative ingress domains per kserve application namespace

Issue - State: open - Opened by philipp1992 4 months ago - 1 comment

#3830 - bufix: update image_transformer.py to handle changes in input structure

Pull Request - State: closed - Opened by zwong91 4 months ago
Labels: lgtm, approved

#3829 - Standardize discovery, installation and usage of LLM functions, agents and tools

Issue - State: open - Opened by pierDipi 4 months ago - 8 comments
Labels: kserve/llm

#3828 - Bump vLLM to 0.5.3.post1

Pull Request - State: closed - Opened by sivanantha321 4 months ago - 2 comments
Labels: lgtm, approved

#3827 - Rename max_length parameter to max_model_len to be in sync with vLLM

Pull Request - State: closed - Opened by Datta0 4 months ago - 1 comment
Labels: lgtm, approved

#3826 - Need to upgrade vLLM version to support Llama3.1

Issue - State: closed - Opened by vdabravolski 4 months ago - 1 comment

#3825 - [Upstream] - Update-istio version based on go version 1.21

Pull Request - State: closed - Opened by mholder6 4 months ago - 1 comment
Labels: lgtm, approved

#3824 - Publish 0.13.1 Release

Pull Request - State: closed - Opened by johnugeorge 4 months ago - 2 comments
Labels: lgtm, approved

#3823 - KServe Storage Initializer to update the Isvc with some status

Issue - State: open - Opened by tarilabs 4 months ago - 4 comments
Labels: kind/feature

#3822 - Upgrade CI deps

Pull Request - State: closed - Opened by sivanantha321 4 months ago - 1 comment
Labels: lgtm, approved

#3821 - 0.13.1 Patch Release

Pull Request - State: closed - Opened by gavrissh 4 months ago - 2 comments
Labels: lgtm, approved

#3820 - Triton Inference Server Doesn't Returning Expected Response on Model Endpoint

Issue - State: open - Opened by Raghul-M 4 months ago

#3819 - Add support for Azure DNS zone endpoints

Pull Request - State: closed - Opened by tjandy98 4 months ago - 3 comments
Labels: lgtm, approved

#3818 - Add support for Azure DNS zone endpoints

Pull Request - State: closed - Opened by tjandy98 4 months ago

#3817 - Incorrect totalCopies values after editing InferenceService

Issue - State: open - Opened by senthilrch 4 months ago - 2 comments

#3816 - fail to locate model file for model <model-name> under dir /mnt/models,trying loading from model repository

Issue - State: closed - Opened by PSKP-95 4 months ago

#3815 - Add HTTP headers to inbound requests to identify isvc name and namespace

Issue - State: closed - Opened by cmaddalozzo 4 months ago - 1 comment
Labels: kserve/control-plane

#3814 - Add support overriding model mount path in model server container

Pull Request - State: open - Opened by davidliu40313 4 months ago - 2 comments

#3813 - Use helm for quick installation

Pull Request - State: closed - Opened by sivanantha321 4 months ago - 2 comments
Labels: lgtm, approved

#3812 - Bump python to 3.11 for serving runtime images and Bump poetry to 1.8.3

Pull Request - State: closed - Opened by sivanantha321 4 months ago - 2 comments
Labels: lgtm, approved

#3811 - Triton In-Process server integration with huggingface

Pull Request - State: open - Opened by sivanantha321 4 months ago - 4 comments

#3810 - Update KServe 2024-2025 Roadmap

Pull Request - State: closed - Opened by yuzisun 4 months ago - 1 comment
Labels: approved

#3809 - Enabling inference service logging disables streaming responses

Issue - State: closed - Opened by jerryharrow 4 months ago - 8 comments
Labels: kind/bug

#3808 - Increase timeout to make unit test stable

Pull Request - State: closed - Opened by Jooho 4 months ago - 6 comments
Labels: lgtm, approved

#3805 - Bump install manifests to v0.13.0

Issue - State: closed - Opened by rimolive 4 months ago - 1 comment
Labels: kind/bug

#3804 - Support Envoy Gateway as ingress option

Issue - State: open - Opened by yuzisun 4 months ago
Labels: kind/feature, kserve/control-plane

#3803 - How to isolate models from worker pods in a multi-tenancy setup

Issue - State: open - Opened by mangalaman93 4 months ago - 1 comment
Labels: kind/feature

#3802 - Install packages needed for vllm model load

Pull Request - State: closed - Opened by gavrissh 4 months ago - 7 comments
Labels: lgtm, approved

#3801 - Tensorflow model Could not find variable

Issue - State: closed - Opened by yashprakashsharma 4 months ago - 1 comment
Labels: kind/bug

#3800 - Support speculative decoding in vLLM backend of HuggingFace server

Issue - State: open - Opened by terrytangyuan 4 months ago - 3 comments
Labels: good first issue, kind/feature

#3799 - TLS with S3 Outside ConfigMap

Issue - State: open - Opened by bwhartlove 4 months ago - 3 comments
Labels: kind/feature

#3798 - Target Model State: Pending

Issue - State: closed - Opened by yage11 4 months ago - 2 comments

#3797 - mlflow model cannot be deployed

Issue - State: open - Opened by yoshie-kosaka 4 months ago - 1 comment
Labels: kind/bug

#3795 - Large model deployment timesout

Issue - State: open - Opened by manstis 4 months ago - 12 comments
Labels: kind/bug

#3794 - Remove ray dependency for the storage-initializer

Issue - State: closed - Opened by mkumatag 4 months ago - 2 comments
Labels: kind/bug

#3793 - s3 storage absolute path issue - initial commit

Pull Request - State: closed - Opened by andyi2it 4 months ago - 1 comment
Labels: do-not-merge/work-in-progress

#3792 - Resource requests and limits not respected / Usage of EmptyDir volume "models-dir" exceeds the limit "1536Mi"

Issue - State: closed - Opened by Zeashh 4 months ago - 3 comments
Labels: kind/bug

#3790 - transformer with v2 + grpc is not work

Issue - State: closed - Opened by todtjs92 4 months ago - 4 comments
Labels: kind/bug

#3789 - Add readiness probe for MLServer and Increase memory for pmml in CI

Pull Request - State: closed - Opened by sivanantha321 4 months ago - 4 comments
Labels: lgtm, approved

#3788 - Several bug fixes for vLLM completion endpoint

Pull Request - State: closed - Opened by sivanantha321 4 months ago - 8 comments
Labels: lgtm, approved

#3787 - chore: allow ray updates

Pull Request - State: closed - Opened by Hojland 4 months ago - 4 comments

#3786 - Fix issue with rolling update behavior

Pull Request - State: closed - Opened by andyi2it 4 months ago - 4 comments
Labels: lgtm, approved

#3785 - Extend the OpenAI schema to support additional parameters

Issue - State: open - Opened by gavrissh 4 months ago
Labels: kind/feature

#3784 - Bump vLLM version in huggingface_server to v0.5.1

Issue - State: closed - Opened by JayDoubleu 4 months ago - 1 comment
Labels: kind/bug, kserve/llm

#3783 - huggingfaceserver: allow transformers updates within the major version

Pull Request - State: open - Opened by isaranto 4 months ago - 4 comments

#3782 - Bump transformers in huggingfaceserver python package

Issue - State: open - Opened by isaranto 4 months ago - 1 comment
Labels: kind/feature

#3781 - [WIP] Model Cache CR

Pull Request - State: closed - Opened by greenmoon55 4 months ago - 2 comments
Labels: do-not-merge/work-in-progress

#3780 - WIP: LayoutLM support

Pull Request - State: open - Opened by andyi2it 4 months ago - 1 comment
Labels: do-not-merge/work-in-progress

#3779 - Make Virtual Service case-insensitive

Pull Request - State: open - Opened by andyi2it 4 months ago - 2 comments

#3778 - ImportError: cannot import name 'BentoService' from 'bentoml' (/usr/local/lib/python3.9/dist-packages/bentoml/init.py)

Issue - State: open - Opened by LOADBC 4 months ago
Labels: kind/bug

#3777 - Fja/feast cache predictions

Pull Request - State: open - Opened by franciscojavierarceo 5 months ago - 1 comment
Labels: do-not-merge/work-in-progress

#3776 - storage initializer container downloads all the folder/files from matching path instead of absolute path

Issue - State: open - Opened by tarukumar 5 months ago - 2 comments
Labels: kind/bug

#3775 - Use add_generation_prompt while creating chat template

Pull Request - State: closed - Opened by Datta0 5 months ago - 7 comments
Labels: lgtm, approved

#3774 - Torchserve security update

Pull Request - State: open - Opened by udaij12 5 months ago - 7 comments
Labels: lgtm, hold

#3773 - Deduplicate the names for the additional domain names

Pull Request - State: open - Opened by houshengbo 5 months ago - 2 comments

#3772 - feat: Adding demo on caching inference output with Feast

Pull Request - State: closed - Opened by franciscojavierarceo 5 months ago - 1 comment
Labels: do-not-merge/work-in-progress

#3771 - Add tests for vLLM

Pull Request - State: closed - Opened by sivanantha321 5 months ago - 4 comments
Labels: lgtm, approved

#3770 - Reconciler error while creating InferenceService: failed to call webhook kserve-webhook-server-service.kserve.svc context deadline

Issue - State: open - Opened by roseaysina 5 months ago - 4 comments
Labels: kind/bug

#3769 - Failed to start model server: integer division or modulo by zero

Issue - State: closed - Opened by hyder 5 months ago - 7 comments
Labels: kind/bug

#3768 - RollingUpdate strategy is not effective for RawDeployment mode

Issue - State: closed - Opened by Syulin7 5 months ago - 3 comments
Labels: kind/bug, kserve/control-plane, kserve/autoscaling

#3767 - CWE-362 - anyio Race Condition

Pull Request - State: closed - Opened by spolti 5 months ago - 5 comments

#3766 - Make inference to models using Istio and keycloak avoiding session cookies

Issue - State: closed - Opened by acardoco 5 months ago - 2 comments
Labels: kind/feature

#3765 - Update aif example

Pull Request - State: closed - Opened by spolti 5 months ago - 2 comments
Labels: lgtm, approved

#3764 - Generate go client for resource list types

Pull Request - State: closed - Opened by sivanantha321 5 months ago - 2 comments
Labels: do-not-merge/work-in-progress

#3763 - Can't find version compatibility matrix for KServe

Issue - State: closed - Opened by roseaysina 5 months ago - 4 comments
Labels: kind/bug

#3762 - Document missing content

Issue - State: open - Opened by zqzzq 5 months ago

#3761 - Update golang for docs/Dockerfile to 1.21

Pull Request - State: closed - Opened by spolti 5 months ago - 4 comments
Labels: lgtm, approved

#3760 - Upgrade docs dockerfile

Pull Request - State: closed - Opened by spolti 5 months ago - 2 comments
Labels: do-not-merge/invalid-owners-file

#3759 - Allow configuring replicas for raw deployments

Pull Request - State: open - Opened by israel-hdez 5 months ago - 7 comments

#3758 - Fix No model ready error in multi model serving

Pull Request - State: closed - Opened by sivanantha321 5 months ago - 8 comments
Labels: lgtm, approved

#3757 - Refactor the ModelServer to let uvicorn handle multiple workers and use 'spawn' for mutiprocessing

Pull Request - State: closed - Opened by sivanantha321 5 months ago - 3 comments
Labels: lgtm, approved

#3756 - duplicated hosts error after configuring the additional domains

Issue - State: open - Opened by yuzisun 5 months ago - 1 comment
Labels: kind/bug

#3755 - fake client returns no kind "ClusterServingRuntimeList" is registered for version "serving/v1alpha1"

Issue - State: open - Opened by tylerhyang 5 months ago - 2 comments
Labels: kind/bug

#3754 - Fix dead links on PyPI

Pull Request - State: closed - Opened by kevinbazira 5 months ago - 4 comments
Labels: lgtm, approved

#3753 - inferenceservice controller: fix error check in Serverless mode

Pull Request - State: closed - Opened by dtrifiro 5 months ago - 2 comments
Labels: lgtm, approved

#3752 - Added secure gRPC server option

Pull Request - State: open - Opened by cbalbera-imaige 5 months ago - 7 comments

#3751 - Protobuf version bump

Pull Request - State: open - Opened by andyi2it 5 months ago - 4 comments

#3750 - Multi-Lora support

Issue - State: open - Opened by skonto 5 months ago - 1 comment
Labels: kind/feature, kserve/llm

#3749 - [WIP] Model cache Example

Pull Request - State: closed - Opened by greenmoon55 5 months ago - 1 comment
Labels: do-not-merge/work-in-progress

#3748 - Getting timeout failed to failed to call webhook: Post "https://kserve-webhook-server-service.default.svc:443/mutate-serving-kserve-io-v1beta1-inferenceservice?timeout=10s"

Issue - State: closed - Opened by shrinivas1998 5 months ago - 7 comments

GitHub / kserve/kserve issues and pull requests