feat(aws-neuron): add mini-sglang-neuron LLM inference framework#8
Open
feat(aws-neuron): add mini-sglang-neuron LLM inference framework#8
Conversation
Clones and installs yottalabsai/mini-sglang-neuron at a pinned commit (e984a5b) during image build. Source remains at /opt/mini-sglang-neuron so server.sh and run_minisgl.sh are accessible at runtime. - Add MINI_SGLANG_NEURON_COMMIT ARG (overridable via bake) - Install ninja (replaces conda-based init_setup.sh dependency) - Pin transformers to >=4.56.0,<4.57.3 as required by minisgl - Add build-time assertion: import minisgl - Bump TAG_SUFFIX to 2026032502
neuronx_distributed_inference (minisgl dependency) is only available on pip.repos.neuron.amazonaws.com, not PyPI.
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
e984a5bduring image build/opt/mini-sglang-neuron—server.shandrun_minisgl.shaccessible at runtimeninjavia pip (replacesconda install ninjafrominit_setup.sh)transformers>=4.56.0,<4.57.3as required byminisglimport minisglTAG_SUFFIX→2026032502to trigger CI rebuildTest plan
docker run --rm $IMAGE python3.11 -c "import minisgl; print('ok')"succeedsdocker run --rm $IMAGE ls /opt/mini-sglang-neuron/server.shshows the file