Code

Code sync for upstream v0.14.0#421

Code

Merged

israel-hdez merged 95 commits intoopendatahub-io:masteropendatahub-io/kserve:masterfrom israel-hdez:j9436-kserve014-upgradeisrael-hdez/kserve:j9436-kserve014-upgradeCopy head branch name to clipboardOct 28, 2024

+242,684-35,090

Commits

Commits on Jun 21, 2024

• Propagate trust_remote_code flag throughout vLLM startup (kserve#3729)

  Show description for 56a4e7d
  

  calwoo

  and

  yuzisun

  authored
  56a4e7d

Commits on Jun 24, 2024

• Fix dead links on PyPI (kserve#3754)

  Show description for 352e030
  kevinbazira

  authored
  352e030

• Fix model is ready even if there is no model (kserve#3275)

  Show description for d19e310
  

  HAO2167

  and

  koshino17

  authored
  d19e310

Commits on Jun 27, 2024

• Fix No model ready error in multi model serving (kserve#3758)

  Show description for fbd8778
  sivanantha321

  authored
  fbd8778

Commits on Jun 29, 2024

• Initial implementation of Inference client (kserve#3401)

  Show description for 74c9ff4
  sivanantha321

  authored
  74c9ff4

• Fix logprobs for vLLM (kserve#3738)

  Show description for d4349ea
  sivanantha321

  authored
  d4349ea

• Fix model name not properly parsed by inference graph (kserve#3746)

  Show description for 68b04ef
  

  sivanantha321

  and

  yuzisun

  authored
  68b04ef

• pillow - Buffer Overflow (kserve#3598)

  Show description for ca691f7
  spolti

  authored
  ca691f7

Commits on Jul 11, 2024

• Use add_generation_prompt while creating chat template (kserve#3775)

  Show description for 164ea83
  Datta0

  authored
  164ea83

Commits on Jul 12, 2024

• Deduplicate the names for the additional domain names (kserve#3773)

  Show description for 1a70e11
  houshengbo

  authored
  1a70e11

Commits on Jul 15, 2024

• Make Virtual Service case-insensitive (kserve#3779)

  Show description for 29731be
  andyi2it

  authored
  29731be

Commits on Jul 18, 2024

• Install packages needed for vllm model load (kserve#3802)

  Show description for 580a0f3
  gavrissh

  authored
  580a0f3

Commits on Jul 20, 2024

• Make gRPC max message length configurable (kserve#3741)

  Show description for 31d2395
  sivanantha321

  authored
  31d2395

• Add readiness probe for MLServer and Increase memory for pmml in CI (kserve#3789)

  Show description for 5736731
  sivanantha321

  authored
  5736731

Commits on Jul 21, 2024

• Several bug fixes for vLLM completion endpoint (kserve#3788)

  Show description for bb9641f
  sivanantha321

  authored
  bb9641f

Commits on Jul 25, 2024

• Increase timeout to make unit test stable (kserve#3808)

  Show description for de96bd3
  Jooho

  authored
  de96bd3

Commits on Jul 27, 2024

• Upgrade CI deps (kserve#3822)

  Show description for 32d3fc0
  sivanantha321

  authored
  32d3fc0

• Add tests for vLLM (kserve#3771)

  Show description for 3862175
  sivanantha321

  authored
  3862175

• Bump python to 3.11 for serving runtime images and Bump poetry to 1.8.3 (kserve#3812)

  Show description for f9e7d5a
  sivanantha321

  authored
  f9e7d5a

Commits on Aug 2, 2024

• Bump vLLM to 0.5.3.post1 (kserve#3828)

  Show description for 96fb00e
  sivanantha321

  authored
  96fb00e

Commits on Aug 6, 2024

• Refactor the ModelServer to let uvicorn handle multiple workers and use 'spawn' for mutiprocessing (kserve#3757)

  Show description for c080da5
  sivanantha321

  authored
  c080da5

Commits on Aug 10, 2024

• Update golang for docs/Dockerfile to 1.21 (kserve#3761)

  Show description for d73f1ca
  spolti

  authored
  d73f1ca

Commits on Aug 11, 2024

• Make ray an optional dependency (kserve#3834)

  Show description for 9632a52
  

  3 peopleauthored
  9632a52

• Update aif example (kserve#3765)

  Show description for a6a061e
  spolti

  authored
  a6a061e

Commits on Aug 12, 2024

• Use helm for quick installation (kserve#3813)

  Show description for f9c73c2
  sivanantha321

  authored
  f9c73c2

Commits on Aug 17, 2024

• Allow KServe to have its own local gateways for Serverless mode (kserve#3737)

  Show description for 2fae6e2
  israel-hdez

  authored
  2fae6e2

• Add support for Azure DNS zone endpoints (kserve#3819)

  Show description for 61b5e7e
  tjandy98

  authored
  61b5e7e

Commits on Aug 18, 2024

• Fix failed build for knativeLocalGatewayService (kserve#3866)

  Show description for a16f2d7
  yuzisun

  authored
  a16f2d7

Commits on Aug 19, 2024

• Add logging request feature for vLLM backend (kserve#3849)

  Show description for 9292c88
  sivanantha321

  authored
  9292c88

Commits on Aug 21, 2024

• Bump vLLM to 0.5.4 (kserve#3874)

  Show description for 656f65e
  sivanantha321

  authored
  656f65e

• Fix: Add workaround for snyk image scan failure (kserve#3880)

  Show description for 99fa478
  sivanantha321

  authored
  99fa478

• Fix trust_remote_code not working with huggingface backend (kserve#3879)

  Show description for 87cf2cd
  sivanantha321

  authored
  87cf2cd

• Update KServe 2024-2025 Roadmap (kserve#3810)

  Show description for e82beb6
  yuzisun

  authored
  e82beb6

Commits on Aug 24, 2024

• Configurable image pull secrets in Helm charts (kserve#3838)

  Show description for c10f548
  saileshd1402

  authored
  c10f548

• Fix issue with rolling update behavior (kserve#3786)

  Show description for 7dd4ae2
  andyi2it

  authored
  7dd4ae2

• Fix the 'tokens exceeding model limit' error response in vllm server (kserve#3886)

  Show description for b89c8c2
  saileshd1402

  authored
  b89c8c2

• Add support for binary data extension protocol and FP16 datatype (kserve#3685)

  Show description for 69cdca5
  

  sivanantha321

  and

  yuzisun

  authored
  69cdca5

• Protobuf version upgrade 4.25.4 (kserve#3881)

  Show description for 0a6302b
  andyi2it

  authored
  0a6302b

• Adds optional labels and annotations to the controller (kserve#3366)

  Show description for a9e967f
  

  3 peopleauthored
  a9e967f

• Enable Server-Side Apply for Kustomize Overlays in Test Environment (kserve#3877)

  Show description for f17d068
  Jooho

  authored
  f17d068

• bufix: update image_transformer.py to handle changes in input structure (kserve#3830)

  Show description for 6978ab9
  

  zwong91

  and

  jongs

  authored
  6978ab9

• support text embedding task in hugging face server (kserve#3743)

  Show description for b7431e2
  

  kevinmingtarja

  and

  yuzisun

  authored
  b7431e2

Commits on Aug 25, 2024

• Rename max_length parameter to max_model_len to be in sync with vLLM (kserve#3827)

  Show description for 1bd82fb
  Datta0

  authored
  1bd82fb

• [Upstream] - Update-istio version based on go version 1.21 (kserve#3825)

  Show description for 74591b4
  mholder6

  authored
  74591b4

Commits on Aug 26, 2024

• Enrich isvc NotReady events for failed conditions (kserve#3303)

  Show description for 9bca4ba
  asdqwe123zxc

  authored
  9bca4ba

• adding metadata on requests (kserve#3635)

  Show description for c05d760
  

  3 peopleauthored
  c05d760

Commits on Aug 27, 2024

• Publish 0.14.0-rc0 release (kserve#3867)

  Show description for ab251d6
  yuzisun

  authored
  ab251d6

Commits on Aug 28, 2024

• Use API token for publishing package to PyPI (kserve#3896)

  Show description for ddc56ca
  sivanantha321

  authored
  ddc56ca

• Fix sdlc broken when kserve installed using helm (kserve#3890)

  Show description for d2f90dc
  sivanantha321

  authored
  d2f90dc

• Add Security Context and Resources to RBAC Proxy (kserve#3898)

  Show description for 3a347c5
  HotsauceLee

  authored
  3a347c5

Commits on Aug 30, 2024

• Remove unwanted cluster scope secret permissions (kserve#3893)

  Show description for e879a39
  sivanantha321

  authored
  e879a39

Commits on Sep 3, 2024

• bump to vllm 0.5.5 (kserve#3911)

  Show description for 67373ad
  lizzzcai

  authored
  67373ad

Commits on Sep 5, 2024

• pin gosec to 2.20.0 (kserve#3921)

  Show description for c80dae9
  greenmoon55

  authored
  c80dae9

Commits on Sep 7, 2024

• add a new doc 'common issues and solutions' (kserve#3878)

  Show description for c7e99d8
  Jooho

  authored
  c7e99d8

• Implement health endpoint for vLLM backend (kserve#3850)

  Show description for 305d393
  sivanantha321

  authored
  305d393

• Add security best practices for inferenceservice, inferencegraph, servingruntimes (kserve#3917)

  Show description for f54e27a
  sivanantha321

  authored
  f54e27a

Commits on Sep 11, 2024

• Bump Go to 1.22 (kserve#3912)

  Show description for e7353d1
  sivanantha321

  authored
  e7353d1

Commits on Sep 13, 2024

• bump to vllm 0.6.0 (kserve#3934)

  Show description for d779344
  hustxiayang

  authored
  d779344

Commits on Sep 15, 2024

• Set the volume mount's readonly annotation based on the ISVC annotation (kserve#3885)

  Show description for fef6c7a
  

  hdefazio

  and

  spolti

  authored
  fef6c7a

Commits on Sep 16, 2024

• mount /dev/shm volume to huggingfaceserver (kserve#3910)

  Show description for 391c8c6
  lizzzcai

  authored
  391c8c6

• Fix permission error in snyk scan (kserve#3889)

  Show description for 9ec6842
  sivanantha321

  authored
  9ec6842

Commits on Sep 17, 2024

• Cluster Local Model CR (kserve#3839)

  Show description for acfc887
  greenmoon55

  authored
  acfc887

• added http headers to inbound request (kserve#3895)

  Show description for 90a5e12
  andyi2it

  authored
  90a5e12

Commits on Sep 19, 2024

• Add prow-github-action (kserve#3888)

  Show description for a2f612c
  sivanantha321

  authored
  a2f612c

• Add TLS support for Inference Loggers (kserve#3863)

  Show description for 02293ac
  ruivieira

  authored
  02293ac

• Fix explainer endpoint not working with path based routing (kserve#3257)

  Show description for 536fc9b
  sivanantha321

  authored
  536fc9b

• Fix ingress configuration for path based routing and update go mod (kserve#3944)

  Show description for d97baa6
  sivanantha321

  authored
  d97baa6

Commits on Sep 23, 2024

• Add HostIPC field to ServingRuntimePodSpec (kserve#3943)

  Show description for a0a4d00
  greenmoon55

  authored
  a0a4d00

• remove conversion wehbook part from self-signed-ca.sh (kserve#3941)

  Show description for bf6fae8
  Jooho

  authored
  bf6fae8

• update fluid kserve sample to use huggingface servingruntime (kserve#3907)

  Show description for 2376eeb
  lizzzcai

  authored
  2376eeb

Commits on Sep 24, 2024

• bump to vLLM0.6.1post2 (kserve#3948)

  Show description for 80982c2
  hustxiayang

  authored
  80982c2

Commits on Sep 26, 2024

• Add NodeDownloadPending status to ClusterLocalModel (kserve#3955)

  Show description for 12c4039
  greenmoon55

  authored
  12c4039

Commits on Sep 27, 2024

• add tags to rest server timing logs to differentiate cpu and wall time (kserve#3954)

  Show description for 9380e99
  gfkeith

  authored
  9380e99

Commits on Sep 29, 2024

• Implement Huggingface model download in storage initializer (kserve#3584)

  Show description for 1e28d4f
  andyi2it

  authored
  1e28d4f

Commits on Sep 30, 2024

• Update OWNERS file (kserve#3966)

  Show description for b344a0a
  yuzisun

  authored
  b344a0a

Commits on Oct 2, 2024

• Cluster local model controller (kserve#3860)

  Show description for 20b6e29
  

  greenmoon55

  and

  yuzisun

  authored
  20b6e29

Commits on Oct 3, 2024

• Prepare for 0.14.0-rc1release and automate sync process (kserve#3970)

  Show description for a50fdc9
  sivanantha321

  authored
  a50fdc9

• add a new API for multi-node/multi-gpu (kserve#3871)

  Show description for d5ed018
  

  Jooho

  and

  yuzisun

  authored
  d5ed018

Commits on Oct 5, 2024

• Fix update-openapigen.sh that can be executed from kserve dir (kserve#3924)

  Show description for ecc3729
  

  Jooho

  and

  yuzisun

  authored
  ecc3729

Commits on Oct 6, 2024

• Add python 3.12 support and remove python 3.8 support (kserve#3645)

  Show description for 24d882b
  sivanantha321

  authored
  24d882b

Commits on Oct 9, 2024

• Fix openssl vulnerability CWE-1395 (kserve#3975)

  Show description for 17725be
  sivanantha321

  authored
  17725be

• Fix Kubernetes Doc Links (kserve#3670)

  Show description for d7d79e1
  

  jyono

  and

  cmaddalozzo

  authored
  d7d79e1

• Fix kserve local testing env (kserve#3981)

  Show description for 70e12ff
  yuzisun

  authored
  70e12ff

Commits on Oct 10, 2024

• Fix streaming response not working properly with logger (kserve#3847)

  Show description for dec8c14
  sivanantha321

  authored
  dec8c14

• Add a flag for automount serviceaccount token (kserve#3979)

  Show description for 6ff2a2f
  greenmoon55

  authored
  6ff2a2f

Commits on Oct 11, 2024

• Do not set security context on the storage initializer from user container (kserve#3985)

  Show description for d2695a5
  greenmoon55

  authored
  d2695a5

• Modelcar race condition mitigation with an init container (kserve#3932)

  Show description for 7796c44
  israel-hdez

  authored
  7796c44

Commits on Oct 12, 2024

• Fix: Headers passing for v1/v2 endpoints (kserve#3669)

  Show description for fc72a2b
  

  andyi2it

  and

  yuzisun

  authored
  fc72a2b

Commits on Oct 14, 2024

• Torchserve security update (kserve#3774)

  Show description for dbceef3
  udaij12

  authored
  dbceef3

• Pin ubuntu 22.04 for minikube setup action (kserve#3994)

  Show description for 82234c0
  greenmoon55

  authored
  82234c0

• KServe 0.14 Release (kserve#3988)

  Show description for 7e43642
  greenmoon55

  authored
  7e43642

Commits on Oct 25, 2024

• Merge remote-tracking branch 'kserve/release-0.14' into j9436-kserve014-upgrade

  Show description for befa4d6
  israel-hdez

  committed
  befa4d6

• Fix poetry lockfiles after v0.14.0 code sync

  Show description for 53de246
  israel-hdez

  committed
  53de246

• Restore compatibility with go v1.21

  Show description for b7a868f
  israel-hdez

  committed
  b7a868f

Commits on Oct 28, 2024

• Merge branch 'odh-master' into j9436-kserve014-upgrade

  israel-hdez

  committed
  c9453bf