chore: drop gated Cosmos-Guardrail1 prefetch from cosmos3 worker image#22
Merged
Merged
Conversation
Guardrails are disabled in worker.py (guardrails=False, #21), so the nvidia/Cosmos-Guardrail1 snapshot (the only gated repo, ~10.8GB) is never loaded at runtime. Remove its prefetch, plus the now-unneeded BuildKit hf_token secret mount / HF_TOKEN export — the remaining prefetched repos (Qwen3 tokenizers, Wan VAEs) are all public (verified gated=False), so the build needs NO HF token. Effect: no token/gate hassle at build time, ~11GB smaller image, faster registry push/pull and pod cold-start. Runtime inference is unchanged (the weights were already unused post-#21). Re-add the download + secret if guardrails are ever turned back on. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Johan-de-R
changed the title
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
What
Remove the
nvidia/Cosmos-Guardrail1prefetch (the only gated repo, ~10.8GB) from the Cosmos worker Dockerfile, plus the now-unneeded BuildKithf_tokensecret mount /HF_TOKENexport.Why it's safe
Guardrails are disabled in
worker.py(guardrails=False, #21 — merged and live in prod as fw-v4), soCosmos-Guardrail1is never loaded at runtime. The weights were baked-but-unused.The remaining prefetched repos are all public (verified via HF API,
gated=False):Qwen/Qwen3-0.6B,Qwen/Qwen3-VL-{2B,8B,32B}-Instruct,Wan-AI/Wan2.1-T2V-14B,Wan-AI/Wan2.2-TI2V-5B.Cosmos-Guardrail1was the solegated=autoone. So the build now needs no HF token (closes the long-standing token/gate hassle — no more Pernekhan-token / gate-click dependency).Effect
Scope / validation
--secret). I validated the token-need removal via repo gated-status, but haven't run a full image build.Cosmos-Guardrail1download +hf_tokensecret if guardrails are ever turned back on (noted inline in the Dockerfile).🤖 Generated with Claude Code