Repository navigation
Fetch Muse Glimmer serving tokenizer files from the non-GGUF repo - #24137
Merged
Merged
Conversation
The CUDA solo-text-batching serving smoke downloaded tokenizer_config.json
and chat_template.jinja from ${HF_MODEL} (meta-models/Muse-Glimmer-30B-GGUF).
That repo only ships GGUF weights, so the download 404s and the job has
failed on every main run since #24010, right after the batching correctness
check passes.
Fetch both files from $TOKENIZER_URL (meta-models/Muse-Glimmer-30B), which is
where tokenizer.json already comes from. Use `curl -f` so a missing file
still fails the job.
Test plan: ran the new download loop locally against $TOKENIZER_URL; both
files downloaded and tokenizer_config.json parses as JSON. `bash -n` passes.
CI: test-muse-glimmer-cuda-e2e-kquant-17gb-solo-text-batching (ciflow/cuda).
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/24137
Note: Links to docs will display an error until the docs builds have been completed. ✅ No FailuresAs of commit 4bec6f4 with merge base 00f0654 ( This comment was automatically generated by Dr. CI and updates every 15 minutes. |
meta-cla
Bot
added
the
CLA Signed
shoumikhin
approved these changes
Oct 24, 2026
Contributor
Author
|
@pytorchbot merge |
|
Mergebot is not configured for this repository. Please use the merge button provided by GitHub. |
This branch was successfully deployed
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
The CUDA solo-text-batching serving smoke downloaded tokenizer_config.json
and chat_template.jinja from ${HF_MODEL} (meta-models/Muse-Glimmer-30B-GGUF).
That repo only ships GGUF weights, so the download 404s and the job has
failed recently even if the main test passed.
Fetch both files from $TOKENIZER_URL (meta-models/Muse-Glimmer-30B), which is
where tokenizer.json already comes from. Use
curl -fso a missing filestill fails the job.
Test plan: ran the new download loop locally against $TOKENIZER_URL; both
files downloaded and tokenizer_config.json parses as JSON.
bash -npasses.CI: test-muse-glimmer-cuda-e2e-kquant-17gb-solo-text-batching (ciflow/cuda).