Admin Bot affb1caa63 feat(gateway): route clef-flash to clef-serve ...

Restores the route removed when the model could not run. It runs now, on a different
runtime: SGLang needs v0.5.22+ which upstream publishes only on CUDA 13, and CUDA 13
dropped Volta kernels. clef-serve loads the same weights through plain transformers in
fp16, sharded over two V100s, and serves the model's own systemone() on /v1/systemone.

Weights measured at 17.75 GiB in BF16; fp16 costs the same bytes per parameter.

2026-10-29 23:06:32 -07:00

..

tekton

fix(ci): relax namespace validation test + add webhook endpoint test (#30)

2026-09-16 03:08:20 +00:00

deployment.yaml

fix(proxy): admission-control review fixes missing from the #65 merge (#66)

2026-09-30 12:19:24 +00:00

gateway-config-secret.yaml

feat(gateway): route clef-flash to clef-serve

2026-10-29 23:06:32 -07:00

grafana-dashboard-llm-metrics.yaml

Add TTFT & ITL Metrics for LLM Inference (#28)

2026-09-15 08:53:58 +00:00

integration-test-job.yaml

feat: add comprehensive integration tests and CI pipeline

2026-09-13 11:42:55 +09:00

kustomization.yaml

feat(webhook): Forgejo package webhook → ArgoCD image promotion (#55)

2026-09-28 02:45:41 +00:00

kustomization.yaml.bak

feat(network): SSE optimization for local LLM streaming (#31 #32 #33) (#26)

2026-09-13 23:37:33 +00:00

network-policy.yaml

fix(gateway): allow egress to ingress-nginx for JWKS

2026-10-27 01:37:08 -07:00

rbac.yaml

feat(sessions): sandbox resource — per-session k8s Pod+PVC+Service (§4.15.4)

2026-09-28 19:53:37 +08:00

service.yaml

chore: initial commit of Go API gateway

2026-08-19 20:54:34 -07:00

serviceaccount.yaml

fix: add serviceaccount manifest (was in deleted rbac.yaml)

2026-08-26 19:49:11 -07:00

smtp-secrets.example.yaml

feat(network): SSE optimization for local LLM streaming (#31 #32 #33) (#26)

2026-09-13 23:37:33 +00:00