fix: remove broken qwen endpoint picker entry#1269
Conversation
|
No actionable comments were generated in the recent review. 🎉 ℹ️ Recent review info⚙️ Run configurationConfiguration used: Path: .coderabbit.yaml Review profile: CHILL Plan: Pro Run ID: 📒 Files selected for processing (2)
💤 Files with no reviewable changes (2)
📝 WalkthroughWalkthroughA Qwen model option ( Changes
Estimated code review effort🎯 1 (Trivial) | ⏱️ ~2 minutes Poem
🚥 Pre-merge checks | ✅ 3✅ Passed checks (3 passed)
✏️ Tip: You can configure your own custom pre-merge checks in the settings. ✨ Finishing Touches📝 Generate docstrings
🧪 Generate unit tests (beta)
Comment |
The inference-config migration (#1265) moved the implementation to src/lib/inference-config.ts. Resolve the merge conflict by keeping the thin shim in bin/lib/ and applying the qwen removal to the new TS source file. Signed-off-by: Aaron Erickson <aerickson@nvidia.com>
ericksoa
left a comment
There was a problem hiding this comment.
LGTM. Resolved merge conflict with TS migration and applied qwen removal to the new source file.
## Summary - remove `Qwen3.5 397B A17B` from the curated NVIDIA Endpoints cloud model picker - keep the rest of the routed inference model handling unchanged ## Why QA has been using `Qwen3.5 397B A17B` as the default validation target for NVIDIA Endpoints onboarding, but the endpoint team has confirmed that this model is currently not working. This PR does **not** claim that the rest of the NVIDIA Endpoints catalog is broken. It only removes the specific known-bad curated picker entry so onboarding defaults and manual QA runs stop selecting it from the built-in list. Related #1161 ## Validation ```bash npx vitest run test/inference-config.test.js npx eslint bin/lib/inference-config.js test/inference-config.test.js npx tsc -p jsconfig.json --noEmit ``` Signed-off-by: Kevin Jones <kejones@nvidia.com> <!-- This is an auto-generated comment: release notes by coderabbit.ai --> ## Summary by CodeRabbit * **Bug Fixes** * Removed Qwen3.5 397B A17B model from available cloud model options. <!-- end of auto-generated comment: release notes by coderabbit.ai --> Signed-off-by: Aaron Erickson <aerickson@nvidia.com> Co-authored-by: Aaron Erickson <aerickson@nvidia.com>
## Summary - remove `Qwen3.5 397B A17B` from the curated NVIDIA Endpoints cloud model picker - keep the rest of the routed inference model handling unchanged ## Why QA has been using `Qwen3.5 397B A17B` as the default validation target for NVIDIA Endpoints onboarding, but the endpoint team has confirmed that this model is currently not working. This PR does **not** claim that the rest of the NVIDIA Endpoints catalog is broken. It only removes the specific known-bad curated picker entry so onboarding defaults and manual QA runs stop selecting it from the built-in list. Related NVIDIA#1161 ## Validation ```bash npx vitest run test/inference-config.test.js npx eslint bin/lib/inference-config.js test/inference-config.test.js npx tsc -p jsconfig.json --noEmit ``` Signed-off-by: Kevin Jones <kejones@nvidia.com> <!-- This is an auto-generated comment: release notes by coderabbit.ai --> ## Summary by CodeRabbit * **Bug Fixes** * Removed Qwen3.5 397B A17B model from available cloud model options. <!-- end of auto-generated comment: release notes by coderabbit.ai --> Signed-off-by: Aaron Erickson <aerickson@nvidia.com> Co-authored-by: Aaron Erickson <aerickson@nvidia.com>
## Summary - remove `Qwen3.5 397B A17B` from the curated NVIDIA Endpoints cloud model picker - keep the rest of the routed inference model handling unchanged ## Why QA has been using `Qwen3.5 397B A17B` as the default validation target for NVIDIA Endpoints onboarding, but the endpoint team has confirmed that this model is currently not working. This PR does **not** claim that the rest of the NVIDIA Endpoints catalog is broken. It only removes the specific known-bad curated picker entry so onboarding defaults and manual QA runs stop selecting it from the built-in list. Related NVIDIA#1161 ## Validation ```bash npx vitest run test/inference-config.test.js npx eslint bin/lib/inference-config.js test/inference-config.test.js npx tsc -p jsconfig.json --noEmit ``` Signed-off-by: Kevin Jones <kejones@nvidia.com> <!-- This is an auto-generated comment: release notes by coderabbit.ai --> ## Summary by CodeRabbit * **Bug Fixes** * Removed Qwen3.5 397B A17B model from available cloud model options. <!-- end of auto-generated comment: release notes by coderabbit.ai --> Signed-off-by: Aaron Erickson <aerickson@nvidia.com> Co-authored-by: Aaron Erickson <aerickson@nvidia.com>
Summary
Qwen3.5 397B A17Bfrom the curated NVIDIA Endpoints cloud model pickerWhy
QA has been using
Qwen3.5 397B A17Bas the default validation target for NVIDIA Endpoints onboarding, but the endpoint team has confirmed that this model is currently not working.This PR does not claim that the rest of the NVIDIA Endpoints catalog is broken. It only removes the specific known-bad curated picker entry so onboarding defaults and manual QA runs stop selecting it from the built-in list.
Related #1161
Validation
Signed-off-by: Kevin Jones kejones@nvidia.com
Summary by CodeRabbit