Skip to content

Releases: weka/wekai

Release list

v6.1.2

v6.1.2 Latest
Latest

Choose a tag to compare

View all tags
@github-actions github-actions released this 12 Aug 16:42
v6.1.2
35a4f80

Install

Prebuilt binaries (linux amd64/arm64, macOS Apple Silicon) are
attached below, e.g.:

curl -fsSL https://github.com/weka/wekai/releases/download/v6.1.2/wekai_v6.1.2_$(uname -s | tr A-Z a-z)_$(uname -m | sed 's/x86_64/amd64/;s/aarch64/arm64/').tar.gz | tar -xz

Benchmark

Replay benchmark against your endpoint (see chart README for all values).
This image embeds the replay artifact, so no volume or fetch step is needed:

helm upgrade --install my-replay oci://quay.io/weka.io/helm/wekai \
  --version v6.1.2 \
  --set endpoint=http://YOUR-LLM-HOST:8000

docker pull quay.io/weka.io/wekai:v6.1.2

Router

Model-aware LLM router with prefix-cache affinity. Separate,
replay-less image — same binary, without the multi-GB replay layer a
router never reads.

Point it at your fleet by pod label. Each discovered pod contributes
its own port, so several DaemonSets on different ports stay one pool:

helm upgrade --install my-router oci://quay.io/weka.io/helm/wekai-router \
  --version v6.1.2 \
  --set-string 'router.backends[0].pods.app=vllm' \
  --set-string 'router.backends[0].port=http'

A static list works the same way, and the two can be mixed:

  --set-string 'router.backends[0]=http://vllm-a:8000' \
  --set-string 'router.backends[1]=http://vllm-b:8000'

Per-model routes, a hosted fallback and credentials are in
docs/router.md.

docker pull quay.io/weka.io/wekai-router:v6.1.2

CLI (binary is named wekai):

go install github.com/weka/wekai@v6.1.2

Full Changelog: v6.1.1...v6.1.2

Assets 5
Loading

v6.0.4

v6.0.4

Choose a tag to compare

View all tags
@github-actions github-actions released this 10 Aug 21:32
v6.0.4
e44e62c

Install

Prebuilt binaries (linux amd64/arm64, macOS Apple Silicon) are
attached below, e.g.:

curl -fsSL https://github.com/weka/wekai/releases/download/v6.0.4/wekai_v6.0.4_$(uname -s | tr A-Z a-z)_$(uname -m | sed 's/x86_64/amd64/;s/aarch64/arm64/').tar.gz | tar -xz

Benchmark

Replay benchmark against your endpoint (see chart README for all values).
This image embeds the replay artifact, so no volume or fetch step is needed:

helm upgrade --install my-replay oci://quay.io/weka.io/helm/wekai \
  --version v6.0.4 \
  --set endpoint=http://YOUR-LLM-HOST:8000

docker pull quay.io/weka.io/wekai:v6.0.4

Router

Model-aware LLM router with prefix-cache affinity. Separate,
replay-less image — same binary, without the multi-GB replay layer a
router never reads:

helm upgrade --install my-router oci://quay.io/weka.io/helm/wekai-router \
  --version v6.0.4 \
  --set router.routes[0]="* => http://vllm-a:8000|http://vllm-b:8000"

docker pull quay.io/weka.io/wekai-router:v6.0.4

CLI (binary is named wekai):

go install github.com/weka/wekai@v6.0.4

Full Changelog: v6.0.3...v6.0.4

Loading

v6.0.3

v6.0.3

Choose a tag to compare

View all tags
@github-actions github-actions released this 10 Aug 20:39
v6.0.3
b3fa1e7

Install

Prebuilt binaries (linux amd64/arm64, macOS Apple Silicon) are
attached below, e.g.:

curl -fsSL https://github.com/weka/wekai/releases/download/v6.0.3/wekai_v6.0.3_$(uname -s | tr A-Z a-z)_$(uname -m | sed 's/x86_64/amd64/;s/aarch64/arm64/').tar.gz | tar -xz

Benchmark

Replay benchmark against your endpoint (see chart README for all values).
This image embeds the replay artifact, so no volume or fetch step is needed:

helm upgrade --install my-replay oci://quay.io/weka.io/helm/wekai \
  --version v6.0.3 \
  --set endpoint=http://YOUR-LLM-HOST:8000

docker pull quay.io/weka.io/wekai:v6.0.3

Router

Model-aware LLM router with prefix-cache affinity. Separate,
replay-less image — same binary, without the multi-GB replay layer a
router never reads:

helm upgrade --install my-router oci://quay.io/weka.io/helm/wekai-router \
  --version v6.0.3 \
  --set router.routes[0]="* => http://vllm-a:8000|http://vllm-b:8000"

docker pull quay.io/weka.io/wekai-router:v6.0.3

CLI (binary is named wekai):

go install github.com/weka/wekai@v6.0.3

Full Changelog: v6.0.2...v6.0.3

Loading

v6.0.2

v6.0.2

Choose a tag to compare

View all tags
@github-actions github-actions released this 10 Aug 20:22
v6.0.2
1a147e8

Install

Prebuilt binaries (linux amd64/arm64, macOS Apple Silicon) are
attached below, e.g.:

curl -fsSL https://github.com/weka/wekai/releases/download/v6.0.2/wekai_v6.0.2_$(uname -s | tr A-Z a-z)_$(uname -m | sed 's/x86_64/amd64/;s/aarch64/arm64/').tar.gz | tar -xz

Benchmark

Replay benchmark against your endpoint (see chart README for all values).
This image embeds the replay artifact, so no volume or fetch step is needed:

helm upgrade --install my-replay oci://quay.io/weka.io/helm/wekai \
  --version v6.0.2 \
  --set endpoint=http://YOUR-LLM-HOST:8000

docker pull quay.io/weka.io/wekai:v6.0.2

Router

Model-aware LLM router with prefix-cache affinity. Separate,
replay-less image — same binary, without the multi-GB replay layer a
router never reads:

helm upgrade --install my-router oci://quay.io/weka.io/helm/wekai-router \
  --version v6.0.2 \
  --set router.routes[0]="* => http://vllm-a:8000|http://vllm-b:8000"

docker pull quay.io/weka.io/wekai-router:v6.0.2

CLI (binary is named wekai):

go install github.com/weka/wekai@v6.0.2

Full Changelog: v6.0.1...v6.0.2

Loading

v6.0.1

v6.0.1

Choose a tag to compare

View all tags
@github-actions github-actions released this 10 Aug 20:08
v6.0.1
46a2132

Install

Prebuilt binaries (linux amd64/arm64, macOS Apple Silicon) are
attached below, e.g.:

curl -fsSL https://github.com/weka/wekai/releases/download/v6.0.1/wekai_v6.0.1_$(uname -s | tr A-Z a-z)_$(uname -m | sed 's/x86_64/amd64/;s/aarch64/arm64/').tar.gz | tar -xz

Benchmark

Replay benchmark against your endpoint (see chart README for all values).
This image embeds the replay artifact, so no volume or fetch step is needed:

helm upgrade --install my-replay oci://quay.io/weka.io/helm/wekai \
  --version v6.0.1 \
  --set endpoint=http://YOUR-LLM-HOST:8000

docker pull quay.io/weka.io/wekai:v6.0.1

Router

Model-aware LLM router with prefix-cache affinity. Separate,
replay-less image — same binary, without the multi-GB replay layer a
router never reads:

helm upgrade --install my-router oci://quay.io/weka.io/helm/wekai-router \
  --version v6.0.1 \
  --set router.routes[0]="* => http://vllm-a:8000|http://vllm-b:8000"

docker pull quay.io/weka.io/wekai-router:v6.0.1

CLI (binary is named wekai):

go install github.com/weka/wekai@v6.0.1

Full Changelog: v6.0.0...v6.0.1

Loading

v6.0.0

v6.0.0

Choose a tag to compare

View all tags
@github-actions github-actions released this 10 Aug 19:53
v6.0.0
a672175

Install

Prebuilt binaries (linux amd64/arm64, macOS Apple Silicon) are
attached below, e.g.:

curl -fsSL https://github.com/weka/wekai/releases/download/v6.0.0/wekai_v6.0.0_$(uname -s | tr A-Z a-z)_$(uname -m | sed 's/x86_64/amd64/;s/aarch64/arm64/').tar.gz | tar -xz

Benchmark

Replay benchmark against your endpoint (see chart README for all values).
This image embeds the replay artifact, so no volume or fetch step is needed:

helm upgrade --install my-replay oci://quay.io/weka.io/helm/wekai \
  --version v6.0.0 \
  --set endpoint=http://YOUR-LLM-HOST:8000

docker pull quay.io/weka.io/wekai:v6.0.0

Router

Model-aware LLM router with prefix-cache affinity. Separate,
replay-less image — same binary, without the multi-GB replay layer a
router never reads:

helm upgrade --install my-router oci://quay.io/weka.io/helm/wekai-router \
  --version v6.0.0 \
  --set router.routes[0]="* => http://vllm-a:8000|http://vllm-b:8000"

docker pull quay.io/weka.io/wekai-router:v6.0.0

CLI (binary is named wekai):

go install github.com/weka/wekai@v6.0.0

Full Changelog: v5.0.2...v6.0.0

Loading

v5.0.2

v5.0.2

Choose a tag to compare

View all tags
@github-actions github-actions released this 10 Aug 15:34
v5.0.2
60a2bc4

Install

Prebuilt binaries (linux amd64/arm64, macOS Apple Silicon) are
attached below, e.g.:

curl -fsSL https://github.com/weka/wekai/releases/download/v5.0.2/wekai_v5.0.2_$(uname -s | tr A-Z a-z)_$(uname -m | sed 's/x86_64/amd64/;s/aarch64/arm64/').tar.gz | tar -xz

Benchmark

Replay benchmark against your endpoint (see chart README for all values).
This image embeds the replay artifact, so no volume or fetch step is needed:

helm upgrade --install my-replay oci://quay.io/weka.io/helm/wekai \
  --version v5.0.2 \
  --set endpoint=http://YOUR-LLM-HOST:8000

docker pull quay.io/weka.io/wekai:v5.0.2

Router

Model-aware LLM router with prefix-cache affinity. Separate,
replay-less image — same binary, without the multi-GB replay layer a
router never reads:

helm upgrade --install my-router oci://quay.io/weka.io/helm/wekai-router \
  --version v5.0.2 \
  --set router.routes[0]="* => http://vllm-a:8000|http://vllm-b:8000"

docker pull quay.io/weka.io/wekai-router:v5.0.2

CLI (binary is named wekai):

go install github.com/weka/wekai@v5.0.2

Full Changelog: v5.0.1...v5.0.2

Loading

v5.0.1

v5.0.1

Choose a tag to compare

View all tags
@github-actions github-actions released this 10 Aug 14:10
v5.0.1
a36406c

Install

Prebuilt binaries (linux amd64/arm64, macOS Apple Silicon) are
attached below, e.g.:

curl -fsSL https://github.com/weka/wekai/releases/download/v5.0.1/wekai_v5.0.1_$(uname -s | tr A-Z a-z)_$(uname -m | sed 's/x86_64/amd64/;s/aarch64/arm64/').tar.gz | tar -xz

Benchmark

Replay benchmark against your endpoint (see chart README for all values).
This image embeds the replay artifact, so no volume or fetch step is needed:

helm upgrade --install my-replay oci://quay.io/weka.io/helm/wekai \
  --version v5.0.1 \
  --set endpoint=http://YOUR-LLM-HOST:8000

docker pull quay.io/weka.io/wekai:v5.0.1

Router

Model-aware LLM router with prefix-cache affinity. Separate,
replay-less image — same binary, without the multi-GB replay layer a
router never reads:

helm upgrade --install my-router oci://quay.io/weka.io/helm/wekai-router \
  --version v5.0.1 \
  --set router.routes[0]="* => http://vllm-a:8000|http://vllm-b:8000"

docker pull quay.io/weka.io/wekai-router:v5.0.1

CLI (binary is named wekai):

go install github.com/weka/wekai@v5.0.1

Full Changelog: v5.0.0...v5.0.1

Loading

v4.8.3

v4.8.3

Choose a tag to compare

View all tags
@github-actions github-actions released this 05 Aug 09:34
v4.8.3
1e7b19d

Install

Prebuilt binaries (linux amd64/arm64, macOS Apple Silicon) are
attached below, e.g.:

curl -fsSL https://github.com/weka/wekai/releases/download/v4.8.3/wekai_v4.8.3_$(uname -s | tr A-Z a-z)_$(uname -m | sed 's/x86_64/amd64/;s/aarch64/arm64/').tar.gz | tar -xz

Helm (replay benchmark against your endpoint — see README for all values):

helm upgrade --install my-replay oci://quay.io/weka.io/helm/wekai \
  --version v4.8.3 \
  --set endpoint=http://YOUR-LLM-HOST:8000

Container image:

docker pull quay.io/weka.io/wekai:v4.8.3

CLI (binary is named wekai):

go install github.com/weka/wekai@v4.8.3

Full Changelog: v4.8.2...v4.8.3

Loading

v4.8.2

v4.8.2

Choose a tag to compare

View all tags
@github-actions github-actions released this 05 Aug 09:00
v4.8.2
4928584

Install

Prebuilt binaries (linux amd64/arm64, macOS Apple Silicon) are
attached below, e.g.:

curl -fsSL https://github.com/weka/wekai/releases/download/v4.8.2/wekai_v4.8.2_$(uname -s | tr A-Z a-z)_$(uname -m | sed 's/x86_64/amd64/;s/aarch64/arm64/').tar.gz | tar -xz

Helm (replay benchmark against your endpoint — see README for all values):

helm upgrade --install my-replay oci://quay.io/weka.io/helm/wekai \
  --version v4.8.2 \
  --set endpoint=http://YOUR-LLM-HOST:8000

Container image:

docker pull quay.io/weka.io/wekai:v4.8.2

CLI (binary is named wekai):

go install github.com/weka/wekai@v4.8.2

Full Changelog: v4.8.1...v4.8.2

Loading