rock 9617bbe814 hold clef-candle at replicas 0 until the image carries the GDN fix ...

candle-vllm PR #5 (the conv fix) could not be merged, so CI has not published
a :sm70 image containing it. Deploying clef against an older :sm70 fails
silently: the delta rule returns zero on all 24 linear-attention layers and
/v1/systemone still answers 200 with well-formed but wrong classifications.

Raise to 1 once a :sm70 build from the fix merge exists.

2026-11-05 09:41:28 +08:00

..

clef-serve

feat(llm-serving): manage clef-serve in git, generated from app.py

2026-10-29 23:23:03 -07:00

clef-candle.yaml

hold clef-candle at replicas 0 until the image carries the GDN fix

2026-11-05 09:41:28 +08:00

clef-serve.yaml

feat(llm-serving): serve clef-flash on candle-vllm

2026-11-05 09:35:47 +08:00

coder-14b-fp16.yaml

fix(llm-serving): set runtimeClassName nvidia on the candle deployment

2026-11-05 09:22:48 +08:00

coder-service.yaml

k8s(llm-serving): client-facing Service for candle-vllm coder

2026-11-04 18:59:56 +08:00

coder.yaml

feat(llm-serving): poimen ingress, 256K coder, and a stable name for the candle-vllm handoff (#90)

2026-11-03 21:47:47 +00:00

embeddings.yaml

fix(llm-serving): podMetadata is not a field on this KServe CRD

2026-10-27 23:55:54 -07:00

kustomization.yaml

feat(llm-serving): serve clef-flash on candle-vllm

2026-11-05 09:35:47 +08:00

networkpolicy.yaml

feat(llm-serving): poimen ingress, 256K coder, and a stable name for the candle-vllm handoff (#90)

2026-11-03 21:47:47 +00:00

qwen3-moe.yaml

feat(llm-serving): manage clef-serve in git, generated from app.py

2026-10-29 23:23:03 -07:00

qwen-cpu.yaml

chore(comfyui): retire the app for good

2026-11-04 03:44:07 +08:00

reasoning-long-service.yaml

feat(llm-serving): poimen ingress, 256K coder, and a stable name for the candle-vllm handoff (#90)

2026-11-03 21:47:47 +00:00

reasoning.yaml

feat(llm-serving): poimen ingress, 256K coder, and a stable name for the candle-vllm handoff (#90)

2026-11-03 21:47:47 +00:00

reranker.yaml

fix(llm-serving): podMetadata is not a field on this KServe CRD

2026-10-27 23:55:54 -07:00