Repository navigation
Conversation
Assisted-by: Claude Code Signed-off-by: Nigel Jones <jonesn@uk.ibm.com>
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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 v0.1.3 image published to ghcr.io was pulled and served, not just a local build of the same Dockerfile.
docs/STATUS.mdnow says so, with the image manifest digest.Run: the published image (every layer's digest verified on download), through
serve.shunder enroot with only the checkpoint mounted and the Hub offline. The 8b on one H100 and the 30b on two (--tensor-parallel-size 2) passede2e_check11/11,probe_check6/6 andaccuracy_check. Speech input on (SYSTEMONE_SPEECH_INPUT=1, model from a mounted cache) passed on the 8b, and with no speech modelserve.shstopped before vLLM started.Docs only. Still not run:
docker runitself, and speech input on with the 30b.