Morph MORPH
SIGN IN SIGN UP
dhruvhead / production-stack UNCLAIMED
0 0 1 Python

COMMITS

main
July 22, 2026
H
docs: use Ray-capable image in KubeRay tutorial (#1000)
Haijie Zhi committed
47bcd73
T
fix(operator): use per-router names for VLLMRouter pod-viewer RBAC (#993)
Tai An committed
001be8f
July 9, 2026
T
fix(operator): tolerate missing KEDA when cleaning up ScaledObject (#985)
Tai An committed
90ddf82
June 25, 2026
R
[Feat][Helm] Add vllmConfig.revision for HuggingFace model version pinning (#961)
Roberto Barreda committed
1e973a3
H
fix(utils): make install-minikube-cluster.sh work on macOS (#970)
Humphrey committed
5261497
S
docs(helm): restore LMCache dashboard explanation in Observability section (#982)
samhoss93 committed
094289c
June 24, 2026
H
[Bugfix] Propagate serviceAccountName to Ray head and worker pods (#968)
Hoony committed
bd05e58
June 23, 2026
S
[Bugfix]: Fix streaming "connection closed" before body consumed in orchestrated disaggregated routing (#960)
shoreline2 committed
7c273ab
June 22, 2026
T
feat(helm/raycluster): pass through annotations and podAnnotations (#980)
Tai An committed
a16f60f
Y
[Router] Add prefix_min_match_length threshold to PrefixAwareRouter (#959)
ywc668 committed
e0c1a2e
June 19, 2026
A
docs: update KEDA autoscaling guide to use integrated monitoring sub-chart (#965)
asalah6 committed
9b78da7
H
fix(router): forward extra /sleep query params (level, mode) to upstream (#969)
Humphrey committed
acb014a
June 18, 2026
N
[Feat] Add per-model custom labels and podLabels to modelSpec (#949)
Nasir Amin committed
c92350d
June 17, 2026
I
[Feat] Add extraVolumes and extraVolumeMounts to routerSpec (#966) (#975)
Immanuel committed
49420e4
I
[Bugfix] Correct default runtime class to nvidia (#974)
Immanuel committed
05bffc4
H
fix(utils): make install-kubectl.sh work on macOS (#976)
Humphrey committed
008e30d
S
build: Upgrade multipart to 0.0.32 (#956)
Shern Shiou Tan committed
0329ef2
June 16, 2026
L
[Bugfix][Router] Sanitize prefiller payload in disagg-prefill (stream, min_tokens) (#971)
lcz^_^ committed
010d488
June 15, 2026
A
[Doc] Add V100 (CC 7.0) legacy GPU deployment tutorial (#973)
Amit Choubey committed
b3e3cb8
May 27, 2026
T
[FEAT][Helm] Support setting env for router (#954)
treydock committed
aef9df4
M
[FEAT] add support for customiziable runtimeClass & podAnnotaions (#958)
Mahmoud committed
48b8e69
May 19, 2026
J
fix tutorial dead url (#947)
Jinjia committed
8909ed7
May 14, 2026
M
[Bugfix][Dashboard] Dedup healthy_pods_total across router replicas (#943)
Michael Basov committed
e2801aa
P
[Bugfix][Router] Fix stale Prometheus endpoint health metrics (#888) (#936)
Prashan Sapkota committed
3e353f5
May 12, 2026
C
Add per-model vLLM observability dashboard (#948)
Clouddude committed
72c2b7f
May 7, 2026
R
[CI/Build] Anchor Chart.yaml version grep to start of line (#944)
Rui Zhang committed
7b9c025
R
Bump chart version to 0.1.11 (#942)
Rui Zhang committed
4fcec0d
Y
[Bugfix][Router] Preserve full backend model metadata in /v1/models (#927)
Yaoming Zhan committed
b3db40e
N
[Bugfix] to shared storage not working with dynamic PV provisioning (#933)
Niccolò Tosato committed
dfe0551
May 6, 2026
M
[Feat][Router] Add per-model request latency histogram (#940)
Michael Basov committed
67307bd