Skip to content

change: promote image_uri_config (DLC frameworks + me-west-1) with whisperx alias fix and test alignment - #6290

Open
Yadan-Wei wants to merge 2 commits into
aws:masterfrom
Yadan-Wei:dlc-config-promote-fixes
Open

Yadan-Wei wants to merge 2 commits into
aws:masterfrom
Yadan-Wei:dlc-config-promote-fixes

Conversation

@Yadan-Wei

Copy link
Copy Markdown
Contributor

Promotes the latest generated image_uri_config to master, plus the fixes needed to pass the sagemaker-core image_uris unit tests.

Config (additive; no version/alias/registry present in master is removed):

  • New serving-framework versions: vllm, sglang, vllm-server, vllm-omni, sglang-server, ray-serve, llama-cpp / llama-cpp-arm64, whisperx.
  • Adds me-west-1 coverage to in-window framework versions; out-of-window versions unchanged.

Fixes:

  • whisperx: drop a spurious "3.8": "3.8.6" version alias so version 3.8 resolves to its own moving minor tag instead of the pinned 3.8.6 tag; latest still points to 3.8.
  • Reclassify llama-cpp-arm64 as a cpu-only processor-schema config (migrated from the whole-tag form) with mirrored uri / reject-gpu-instance / literal-tag coverage.
  • Relax the tensorflow latest-vs-previous-release registries test to a subset check, so the newest version may additionally carry a newly launched region still inside the image-copy window.

Supersedes the same-repo promotion PR (could not push fixes onto that branch).

sagemaker-bot and others added 2 commits September 17, 2026 22:24
…e_uri tests

- whisperx: drop the spurious "3.8": "3.8.6" version alias so version 3.8 resolves to its
  own moving minor tag (3.8-cu128-amzn2023-sagemaker) rather than the pinned 3.8.6 tag; the
  latest alias still points to 3.8.
- tests: reclassify llama-cpp-arm64 as a cpu-only processor-schema config (migrated from the
  whole-tag form) with mirrored uri / reject-gpu-instance / literal-tag coverage.
- tests: allow the newest tensorflow version to additionally carry a newly launched region
  that is still inside the image-copy window (subset check instead of exact equality).
@github-actions

github-actions Bot commented Sep 18, 2026

Copy link
Copy Markdown

Claude finished @Yadan-Wei's task in 2m 24s —— View job


Code review

Reviewed the full diff plus the resulting whisperx.json and the serving-framework test helper. This is a generated config promotion; I focused on the hand-authored fixes and on invariants a generator can silently get wrong. Overall it looks sound and the test changes are reasonable. Two things to confirm.

Note: the inline-comment tool isn't available in this run, so findings are consolidated here with file references.


1. whisperx: the two versions have divergent registry maps — latest/3.8 does not get me-west-1 (medium, please confirm)

whisperx.json now has two versions that resolve to the same underlying image (both container_version.gpu = cu128-amzn2023-sagemaker, differing only by tag_prefix 3.8 vs 3.8.6), yet their registries maps differ in both directions:

  • 3.8 (versions."3.8".registries) contains cn-north-1, cn-northwest-1, us-gov-east-1, us-gov-west-1 but not me-west-1.
  • 3.8.6 (versions."3.8.6".registries) contains me-west-1 but not the cn / us-gov partitions above.

Because version_aliases.latest = "3.8", the version most users actually pull (latest, and the bare moving tag 3.8) is the one that is missing me-west-1 — which undercuts this PR's stated goal ("adds me-west-1 coverage to in-window framework versions"). Conversely the pinned 3.8.6 loses the cn/gov coverage that 3.8 has.

If 3.8 and 3.8.6 are the same build, their region availability should match. Please confirm this asymmetry reflects real ECR availability (e.g. the mutable 3.8 tag genuinely hasn't been republished to me-west-1 yet) rather than a generation artifact. Note the existing test_gpu_only_processor_serving_framework_uris won't catch this — it validates each version against its own registry list.

2. Edited config files lost their trailing newline (minor)

Every edited JSON config now ends with } and no trailing newline (the diffs show \ No newline at end of file on the new side only — the base files ended with }\n). Affects all 13 changed image_uri_config/*.json files. This is cosmetic, but if the repo runs an end-of-file-fixer / black-style pre-commit or has an .editorconfig requiring a final newline, it'll flag these. Worth having the generator emit a trailing newline to avoid churn on every future promotion.


Looks good

  • tensorflow test relaxation (test_tensorflow.py): the subset check (reference ⊆ latest) is correct — it still catches regions/accounts dropped from the newest release while tolerating a newly launched region that hasn't been backfilled onto the reference version. Good.
  • cpu-only serving tests (test_dlc_serving_frameworks.py): the new CPU_ONLY_PROCESSOR_FILES path mirrors the gpu-only case cleanly (cpu tail resolution, optional instance_type, gpu-instance rejection), and emptying WHOLE_TAG_CONFIG_FILES is consistent with migrating llama-cpp-arm64 to the processor schema.
  • llama-cpp / llama-cpp-arm64 / ray-serve / vllm- / sglang- additive changes**: version reordering + new versions look additive; spot-checked that ray-serve 1.4 retains its cn-north-1/cn-northwest-1/us-gov-* registries (they moved in the textual diff but are preserved).
  • No security/credential concerns — pure data + test changes.
    · branch dlc-config-promote-fixes

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