feat(llm-serving): serve clef-flash on candle-vllm (#109 )

Co-authored-by: rock <[email protected]>
2026-11-05 01:40:42 +00:00
1 changed files with 1 additions and 6 deletions
@@ -7,12 +7,7 @@ metadata:
    app.kubernetes.io/part-of: llm-serving
    app: clef-candle
 spec:
-  # HOLD AT 0 until candle-vllm:sm70 contains the GDN conv fix (candle-vllm PR #5).
+  replicas: 1
  # An older :sm70 zeroes the key channel band, starves the delta rule and makes
  # every linear-attention layer return zero. The response is still HTTP 200 and
  # well formed, so the failure is silent. Raise to 1 only after CI publishes a
  # :sm70 build from the merge that carries the fix.
  replicas: 0
  strategy:
    # One replica holds one GPU, so Recreate keeps the rollout to a single
    # weights load instead of needing a second card for a surge pod.