Skip to content
Merged
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion kubernetes/apps/ai/llmkube/models/qwen36-27b-sglang.yaml
Original file line number Diff line number Diff line change
Expand Up @@ -77,7 +77,7 @@ spec:
runtime: sglang
# Operator default binds :: (IPv6-only on this IPv4 cluster); override to v4.
bindAddress: 0.0.0.0
image: ghcr.io/tanguille/sglang-rdna4:v0.5.16-gfx1201@sha256:7ed88348a9ba70659a9a149c80e0b79d617f031011ec216b85372f7a56e261a6
image: ghcr.io/tanguille/sglang-rdna4:v0.5.16-gfx1201@sha256:615cb4265400f5468da4c32221f0086df075b126ce8dbfa78d998e844a5e424d

Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

🗄️ Data Integrity & Integration | 🟠 Major | ⚡ Quick win

Invalidate the hi-cache when changing the image digest.

The image digest changes here, but SGLANG_HICACHE_FILE_BACKEND_STORAGE_DIR remains /hicache/sglang-v0.5.16_awq-f541031d at Lines 124-127. The manifest explicitly says this suffix must change with the image digest; otherwise the new container may reuse stale KV pages. Update the suffix or explicitly invalidate the old cache in this change.

🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.

In `@kubernetes/apps/ai/llmkube/models/qwen36-27b-sglang.yaml` at line 80, Update
SGLANG_HICACHE_FILE_BACKEND_STORAGE_DIR in the manifest to use a new
cache-directory suffix matching the changed image digest, rather than
/hicache/sglang-v0.5.16_awq-f541031d; ensure the old hi-cache cannot be reused.

containerPort: 30000
endpoint:
# v0.9.8 maps endpoint.port to both Service port and targetPort; use the
Expand Down