kserve/kserve issues and pull requests

#3543 - There is an invalid link in OPENSHIFT_GUIDE.md

Issue - State: closed - Opened by marek-veber 6 months ago
Labels: kind/bug

#3542 - Move Inference Graph raw test to raw CI/CD workflow

Issue - State: closed - Opened by andyi2it 6 months ago
Labels: kind/bug

#3541 - [Solution] Ray Serve version compatibility issue: cannot import name 'RayServeHandle' from 'ray.serve.handle'

Issue - State: closed - Opened by cceyda 6 months ago - 8 comments
Labels: kind/bug

#3539 - Initial commit for OCI dist spec v1.1.0 agent support

Pull Request - State: open - Opened by rchincha 6 months ago - 5 comments
Labels: do-not-merge/work-in-progress

#3538 - Prevent AttributeError in stop method of ModelServer class

Pull Request - State: closed - Opened by serdarildercaglar 6 months ago - 2 comments

#3537 - Pad left for decode-only architecture llm models

Issue - State: closed - Opened by sivanantha321 6 months ago
Labels: kind/bug

#3536 - Explicitly specify pad token id when generating tokens

Issue - State: closed - Opened by sivanantha321 6 months ago
Labels: kind/bug

#3535 - Explicitly specify pad token id when generating tokens

Pull Request - State: closed - Opened by sivanantha321 6 months ago - 1 comment

#3534 - Only pad left for decode-only architecture models.

Pull Request - State: closed - Opened by sivanantha321 6 months ago - 2 comments
Labels: lgtm, approved

#3533 - transformer<->predictor deployment communication issue? 502 Bad Gateway

Issue - State: closed - Opened by cceyda 6 months ago - 1 comment
Labels: kind/bug

#3531 - Remove white background for the kserve diagram

Pull Request - State: closed - Opened by yuzisun 7 months ago - 1 comment
Labels: approved

#3530 - Update kserve cake diagram

Pull Request - State: closed - Opened by yuzisun 7 months ago - 2 comments
Labels: lgtm, approved

#3529 - Upgrade istio to 1.20 works for the Github Actions

Pull Request - State: closed - Opened by houshengbo 7 months ago - 2 comments
Labels: lgtm, approved

#3528 - Verify if istio 1.18 works fine with knative 1.13

Pull Request - State: closed - Opened by houshengbo 7 months ago - 1 comment

#3527 - Verify if istio 1.17 works fine with knative 1.13

Pull Request - State: closed - Opened by houshengbo 7 months ago - 1 comment

#3526 - In the inference graph, does the serviceName field require the inference service name to be the same as the model name?

Issue - State: closed - Opened by yolk-pie-L 7 months ago - 1 comment

#3525 - Setting timeout not effective

Issue - State: closed - Opened by yolk-pie-L 7 months ago - 1 comment
Labels: kind/bug

#3524 - Update KServe project description

Pull Request - State: closed - Opened by yuzisun 7 months ago - 1 comment
Labels: lgtm, approved

#3523 - Remove GOARCH

Pull Request - State: closed - Opened by mkumatag 7 months ago - 2 comments
Labels: lgtm, approved

#3522 - Is it possible to inject custom initContainer into the InferenceService pod ?

Issue - State: closed - Opened by bpradipt 7 months ago - 1 comment

#3521 - Selected Inference Services predictions in Inference Graph steps to be output together per request

Issue - State: open - Opened by asd981256 7 months ago
Labels: kserve/inference_graph

#3520 - GH Alert: Potential file inclusion via variable

Pull Request - State: closed - Opened by spolti 7 months ago - 2 comments
Labels: lgtm, approved

#3519 - Fix code scanning alert - Potential file inclusion via variable

Issue - State: closed - Opened by spolti 7 months ago

#3518 - Add support for providing storage uri as model_dir

Pull Request - State: closed - Opened by sivanantha321 7 months ago - 4 comments
Labels: do-not-merge/work-in-progress

#3517 - Make the modelcar injection idempotent

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

#3516 - hugging face demo does not work in my local environment

Issue - State: open - Opened by yolk-pie-L 7 months ago - 2 comments
Labels: area/docs

#3515 - You need to specify either `text` or `text_target`

Issue - State: closed - Opened by yolk-pie-L 7 months ago - 1 comment
Labels: kind/bug

#3514 - Cannot scale down inferenceservice pod to zero replica

Issue - State: open - Opened by kwjerrychan 7 months ago - 6 comments
Labels: kind/bug

#3513 - Triton model inference with yolov8 onnx

Issue - State: open - Opened by Al4DIN 7 months ago - 1 comment
Labels: kind/bug

#3512 - HTTP 404 Not Found: Deploying Sklearn-Iris Inference Service on KServe 0.10.0 Using RawDeployment Mode

Issue - State: closed - Opened by BosiDC 7 months ago - 1 comment

#3511 - switch e2e test inference graph to raw mode

Pull Request - State: closed - Opened by andyi2it 7 months ago - 2 comments
Labels: lgtm, approved

#3510 - fix for extract zip from gcs

Pull Request - State: closed - Opened by andyi2it 7 months ago - 3 comments
Labels: lgtm, approved

#3509 - CVE-2024-28110 security upgrade

Pull Request - State: closed - Opened by andyi2it 7 months ago - 2 comments
Labels: lgtm, approved

#3508 - What types of models does the Hugging Face runtime support?

Issue - State: open - Opened by yolk-pie-L 7 months ago - 2 comments
Labels: kserve/huggingface

#3507 - [WIP] Lora module support for HF and VLLM

Pull Request - State: open - Opened by Datta0 7 months ago - 1 comment
Labels: do-not-merge/work-in-progress

#3506 - Sample inference deployed using the modelcar functionality is not starting

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

#3504 - Introduce v2 completions endpoint

Pull Request - State: closed - Opened by gavrishp 7 months ago - 3 comments
Labels: do-not-merge/work-in-progress

#3503 - swith graph to raw e2e tests

Pull Request - State: closed - Opened by muthuraj-i2i 7 months ago - 1 comment

#3502 - Fix isADirectoryError in Azure blob download

Pull Request - State: closed - Opened by tjandy98 7 months ago - 2 comments
Labels: lgtm, approved

#3501 - Storage Initializer Azure IsADirectoryError

Issue - State: closed - Opened by tjandy98 7 months ago - 1 comment
Labels: kind/bug

#3500 - Probe envoy proxy before marking Ingress ready

Pull Request - State: open - Opened by sivanantha321 7 months ago - 3 comments

#3499 - Sample model failing to launch,"No such file or directory: '/mnt/models'" inside the inference service pod.

Issue - State: closed - Opened by wassimMsw 7 months ago - 11 comments
Labels: kind/bug

#3498 - ci: Bump minikube version to work with newer K8s version

Pull Request - State: closed - Opened by terrytangyuan 7 months ago - 3 comments
Labels: lgtm, approved

#3497 - Wrong request uri?

Issue - State: open - Opened by d0m3n1cc 7 months ago - 3 comments

#3496 - Update cert manager version in quick install script

Pull Request - State: closed - Opened by shauryagoel 7 months ago - 2 comments
Labels: lgtm, approved

#3495 - Add Google Cloud Storage support to Storage Spec

Pull Request - State: open - Opened by tjandy98 7 months ago - 7 comments

#3493 - remove unnecessary Istio settings from quick_install.sh

Pull Request - State: closed - Opened by peterj 7 months ago - 3 comments
Labels: lgtm, approved

#3492 - feat: Provide minimal distribution of CRDs

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

#3491 - Fix: fix a typo in qpext doc

Pull Request - State: closed - Opened by daixiang0 7 months ago - 3 comments
Labels: lgtm, approved

#3490 - fix the quote format same with others and docstrings

Pull Request - State: closed - Opened by leyao-daily 7 months ago - 2 comments
Labels: lgtm, approved

#3489 - Make storage initializer install only what is needed for it to run

Issue - State: open - Opened by spolti 7 months ago - 1 comment
Labels: kind/feature

#3488 - Upgrade orjson to version 3.9.15

Pull Request - State: closed - Opened by spolti 7 months ago - 3 comments
Labels: lgtm, approved

#3487 - InferenceService CRD is too large

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

#3486 - fix: Skip domain validation if ingress creation is disabled. Fixes #3485

Pull Request - State: closed - Opened by terrytangyuan 7 months ago - 3 comments
Labels: lgtm

#3485 - Domain validation should be skipped if ingress creation is disabled

Issue - State: closed - Opened by terrytangyuan 7 months ago
Labels: kind/bug

#3484 - chore: Update list of reviewers

Pull Request - State: closed - Opened by ckadner 7 months ago - 5 comments
Labels: lgtm, approved, community/maintenance, area/project-health, kind/process

#3483 - fix: Service existence check should check all spec fields

Pull Request - State: closed - Opened by terrytangyuan 7 months ago - 2 comments
Labels: lgtm

#3482 - [Documentation] IRSA example is not working

Issue - State: open - Opened by kuzm1ch 7 months ago - 3 comments
Labels: kind/bug, area/docs, kfserving/storage

#3481 - Fix bug: Remove redundant helm chart affinity on predictor CRD

Pull Request - State: closed - Opened by trojaond 7 months ago - 3 comments
Labels: lgtm, approved

#3480 - update fastapi>=0.108.0 && unicorn>=0.21.1

Pull Request - State: closed - Opened by gujingit 7 months ago - 6 comments
Labels: lgtm

#3479 - feat: Support customizable deployment spec for RawDeployment mode

Pull Request - State: closed - Opened by terrytangyuan 7 months ago - 2 comments
Labels: do-not-merge/work-in-progress

#3478 - Pytorch V2 Protocol case is not working

Issue - State: closed - Opened by lswjkllc 7 months ago - 6 comments
Labels: kind/bug

#3477 - OpenAI schema

Pull Request - State: closed - Opened by tessapham 7 months ago - 2 comments
Labels: lgtm, approved

#3476 - Remove conversion webhook from manifests

Pull Request - State: closed - Opened by Jooho 7 months ago - 9 comments
Labels: lgtm, approved

#3475 - add support for async streaming in predict

Pull Request - State: closed - Opened by alexagriffith 7 months ago - 2 comments
Labels: lgtm, approved

#3474 - Serverless install: real DNS kills routing

Issue - State: open - Opened by dsgli 7 months ago - 13 comments
Labels: kind/bug

#3473 - Kserve Model Deployment issue

Issue - State: open - Opened by amacharya 7 months ago - 4 comments
Labels: kind/bug

#3472 - Enhance controller setup based on available CRDs

Pull Request - State: closed - Opened by israel-hdez 7 months ago - 13 comments
Labels: lgtm, approved

#3471 - Agriffith50/support async

Pull Request - State: closed - Opened by alexagriffith 7 months ago - 1 comment
Labels: do-not-merge/work-in-progress

#3470 - Enhance manager setup based on available CRDs

Issue - State: closed - Opened by israel-hdez 7 months ago - 1 comment
Labels: kind/feature

#3469 - Remove cluster level list/watch for configmaps, serviceaccounts, secrets

Pull Request - State: closed - Opened by sivanantha321 7 months ago - 20 comments
Labels: lgtm, approved

#3468 - support s390x arch for some python based images ( Ex ray , py-spy )

Issue - State: open - Opened by modassarrana89 7 months ago - 1 comment
Labels: kind/feature

#3467 - Controller out-of-memory kill when cluster has too many secrets

Issue - State: closed - Opened by israel-hdez 7 months ago - 1 comment
Labels: kind/bug

#3466 - fix: Add 'model_version' to InferResponse in python library

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

#3465 - python: 'model_version' argument missing from `InferResponse` class

Issue - State: closed - Opened by ajstewart 7 months ago
Labels: kind/bug

#3464 - Fix:Support Parallelism in vllm runtime

Pull Request - State: closed - Opened by gavrishp 7 months ago - 2 comments
Labels: lgtm, approved

#3463 - Change `certificate` to `ca_bundle` in json style of s3 storageSecret

Pull Request - State: closed - Opened by Jooho 7 months ago - 2 comments
Labels: lgtm, approved

#3462 - The 'certificate' in the storage-config secret conflicts with ModelMesh

Issue - State: closed - Opened by Jooho 7 months ago
Labels: kind/feature

#3461 - Provide Text generation usage metrics

Issue - State: open - Opened by johnugeorge 7 months ago - 1 comment
Labels: kserve/llm

#3460 - Add files via upload

Pull Request - State: closed - Opened by Syntax-Error-1337 7 months ago - 3 comments

#3459 - Fix: Support model parallelism in HF transformer

Pull Request - State: closed - Opened by gavrishp 7 months ago - 2 comments
Labels: lgtm, approved

#3458 - Publish v0.12.0 release

Pull Request - State: closed - Opened by sivanantha321 7 months ago - 2 comments
Labels: lgtm, approved

#3457 - upgrade knative to 1.13

Pull Request - State: closed - Opened by andyi2it 7 months ago - 2 comments
Labels: lgtm, approved

#3456 - Fix: vllm backend does not work with model_dir for huggingface runtime

Pull Request - State: closed - Opened by yuzisun 7 months ago - 1 comment
Labels: lgtm, approved

#3455 - Inference graph router can't resolve domain for node without coredns pod

Issue - State: closed - Opened by ming-afk 7 months ago - 1 comment
Labels: kind/bug

#3454 - Propose transitioning KServe project from LFAI to CNCF

Issue - State: open - Opened by yuzisun 7 months ago

#3453 - `predictor.model.args` defined in `InferenceService` does not override `containers.args` in `ServingRuntime`

Issue - State: closed - Opened by averyngo34 7 months ago - 3 comments
Labels: kind/bug

#3452 - Ability to change parameters of of the default `Deployment` created from `ServingRuntime` and `InferenceService`

Issue - State: closed - Opened by averyngo34 7 months ago - 6 comments
Labels: kind/feature

#3451 - Ability to change parameters of of the default `initContainer` `storage-initializer`

Issue - State: closed - Opened by averyngo34 7 months ago - 4 comments
Labels: kind/feature

#3450 - Fix: Add padding and truncation in huggingface tokenizer

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

#3448 - Fix: bugs for huggingface runtime template

Pull Request - State: closed - Opened by yuzisun 7 months ago - 1 comment
Labels: lgtm, approved

#3446 - vllmserver：did not find expected '-' indicator

Issue - State: open - Opened by AlexFly666 8 months ago - 11 comments
Labels: kind/bug, kserve/llm

#3445 - Serve the large language model with InferenceService，report an error：'type': 'InternalServerException', 'message': 'Worker died.'

Issue - State: open - Opened by AlexFly666 8 months ago
Labels: kind/bug, kfserving/torchserve

GitHub / kserve/kserve issues and pull requests