Situation

In The Last Post I Fine-Tuned Muse Glimmer 30B To Call Tools Better, Found It Calling Tools Everywhere, Added Negative Examples, And Picked Checkpoint 200 Out Of The Second Run. It Ended With One Honest Line: I Hadn’t Merged Or Shipped Any Of It.

This Post Is The Shipping Part. The Adapter Was Trained With PEFT On A Single 48GB GPU. The Model Actually Runs On A 32GB Mac Studio, Through MLX, As A 4-Bit Model Behind A Small Shim Service. Those Two Worlds Don’t Share A File Format, And The Mac Doesn’t Have Much Room To Spare.

Continue reading

Situation

My Local Muse Glimmer 30B Kept Leaking Its Own Tool-Calling Markers Into Replies, So I Planned To Fix It At The Source With A QLoRA Fine-Tune Instead Of Patching The Parser Again. Before Training Anything I Ran A Baseline Eval And It Said Leak Rate 0%, Parallel Calls 2%. Both Numbers Looked Wrong, So I Opened The Raw Outputs And Found Every Single One Contained <| Tokens. The Metric Was Broken, Not The Model. I Fixed It, Concluded The Parser Was Already Enough, And Trained Anyway As An Experiment. Version One Made Parallel Tool Calls Work Almost Perfectly And Also Made The Model Call A Tool On Two Thirds Of Questions That Needed None.

Continue reading

Situation

I Was Cleaning Up My Personal AWS Account Recently And Glue Kept Showing Up Near The Top Of The Bill, Around $10 A Month. As Far As I Know I’m Not Running Any Glue Jobs Right Now, So I Went After The Usual Suspects First: Jobs, Dev Endpoints, Interactive Sessions, Triggers, Workflows. All Of Them Were Already At Zero. The Next Month’s Bill Didn’t Move. Grouping The Cost By Usage Type Finally Showed Where It Came From: Every Cent Was USE1-Crawler-DPU-Hour, Three Crawlers In us-east-1 With No Schedule On Them, Created Back In 2024-04 By The Official CUR CloudFormation Template.

Continue reading

Situation

Been Looking At New Models Lately, And Came Across Muse Glimmer, A 30B Model That’s Supposed To Be Really Good For Personal Use. Wanted To See If It Could Replace Gemma-4 As My Log-Summarizer Backend, Plus A Similar Role On My Personal Assistant. LM Studio Was Already Running On This Machine, So I Just Tried Loading It There. It Failed Immediately:

No module named 'mlx_vlm.speculative.drafters.muse_glimmer'

Continue reading

Situation

Had A Working GCP Weekly Digest Running On Google Apps Script For Weeks — Pulls Release Notes And Blog RSS Every Friday, Hands Them To Gemini To Write A Categorized Digest, Emails It Out, Archives A Copy To Google Drive. The Original Plan Was To Leave It Alone Until It Hit A Real Limit. Then A Different Reason To Migrate Showed Up: Wanted To Write This Up Next To The AWS Version As An “AWS vs GCP Serverless Digest Bot” Comparison, And Apps Script’s GmailApp/DriveApp/ScriptApp.getOAuthToken() Assume Every Reader Already Lives Inside A Google Account — Rebuilt It On Cloud Run Instead, Skipping The Original Migration Threshold On Purpose.

Continue reading

Situation

Part 1 Ended With Two Unresolved Questions: A 250Mi Memory Target For A Dashboard Container Actually Using Only 24Mi, Sitting Suspiciously Close To The 256Mi Limit Already On The Deployment, With No Citable Reason Why. And A CPU Number That Had Never Once Caught My Attention, The One I’d Waved Through Without Checking. The Plan Was To Let It Accumulate History And Come Back To See Which Way The Memory Target Went. A Month Later It Went A Third Way I Hadn’t Considered, The Answer Had Nothing To Do With The Limit, And It Closed Both Questions At Once.

Continue reading

Situation

Had Already Set Up VPA On A GKE Workload (A ClickHouse Backend, After It OOM’d Twice) And Assumed — Wrongly — That Vertical Pod Autoscaler Was Something GKE Provided As A Managed Feature. Turns Out The “Enable” Button On GKE Is Just Google’s Wrapper Around The Same Open-Source kubernetes/autoscaler Project Anyone Can Install Anywhere. Wanted To Confirm That For Real, So I Put It On A 6-Node Homelab RKE2 Cluster With No Cloud Provider In Sight.

It Went In Clean. What Wasn’t Clean Was The First Recommendation It Handed Back For A Live Workload — Ten Times The Container’s Actual Memory Usage, Within Minutes Of Being Installed.

Continue reading