Skip to content

docs: add Modal GPU serving guide - #424

Open
felipeocampoos wants to merge 1 commit into
mainfrom
docs/modal-gpu-serving
Open

docs: add Modal GPU serving guide#424
felipeocampoos wants to merge 1 commit into
mainfrom
docs/modal-gpu-serving

Conversation

@felipeocampoos

Copy link
Copy Markdown
Collaborator

Summary

  • How we used Modal as a drop-in replacement for MIT SLURM GPU partitions during the BODHI-Medcalc rerun campaign, when MIT's GPU QOS was maxed out
  • One-class-per-model vLLM serving pattern, deployable in a few minutes
  • The seven gotchas that actually cost time: silent GPU-quota exhaustion (max_containers), TP=2+AWQ hangs, incomplete client venvs, the checkpoint-hash relaunch trap, per-model SLURM time limits, HF Hub rate-limiting, NFS cache races

Why

Sebastian asked for a shareable writeup so others on the team can use Modal when the MIT GPU queue is full, without rediscovering the same gotchas.

🤖 Generated with Claude Code

How we used Modal as a drop-in replacement for MIT SLURM GPU partitions
during the BODHI-Medcalc rerun campaign (Sept 2026), when MIT's GPU QOS
was maxed out. Covers the one-class-per-model vLLM serving pattern and
the seven gotchas that cost real time: silent GPU-quota exhaustion
without max_containers, TP=2+AWQ hangs, incomplete client venvs, the
checkpoint-hash relaunch trap, per-model SLURM time limits, HF Hub
rate-limiting on concurrent dataset loads, and NFS cache races.

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Copilot AI lite review requested due to automatic review settings September 7, 2026 15:54

Copilot AI left a comment

Copy link
Copy Markdown

Choose a reason for hiding this comment

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

Copilot was unable to review this pull request because the user who requested the review has reached their quota limit.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants