Add disaggregated inference (P/D) on Neuron sample#15
Open
yahavb wants to merge 1 commit into
Open
Conversation
New EKS sample (disagg_serve_vllm/) for prefill/decode disaggregated serving with vLLM on Trn2/Trn3: - DRA-based Neuron + EFA device allocation (co-located devicegroup8 claim) - NIXL/LIBFABRIC KV transfer over EFA - 1P1D skeleton with dynamic xPyD kubectl scale - routing via vLLM production-stack and AIBrix (pd algorithm) - tutorial README + cluster/nodegroup/claim/deploy manifests Also bumps ray to 2.55.0 in the Llama 3.1 finetune sample to clear two Dependabot alerts (GHSA-mw35-8rx3-xf9r high RCE, GHSA-q5fh-2hc8-f6rq moderate DoS).
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
Adds a new EKS sample —
disagg_serve_vllm/— demonstrating disaggregated inference (prefill/decode separation) with vLLM on AWS Neuron (Trn2/Trn3).Contents
disagg_serve_vllm/README.md) — announces DI on Neuron, walks through EKS setup, ends with request examples against both routers.xl-lnc2-trn2-efa-rct.yamlpairs Neuron + EFA devices in onedevicegroup8-constrained ResourceClaimTemplate so the NIXL/LIBFABRIC path is valid; references the Neuron and EFA DRA driver docs.trn2-48xl-efa-ng.yaml(efaEnabled,privateNetworking, capacity reservation) andcluster.yaml.prefill-deploy.yaml(kv_producer) /decode-deploy.yaml(kv_consumer), withkubectl scaleexamples for dynamic xPyD.production-stack-router-deploy.yaml(vLLM production-stack) andaibrix-router-deploy.yaml(AIBrixpdalgorithm, shipped in v0.7.0).Root
README.mdinference table updated with the new sample.Also
rayto 2.55.0 in the Llama 3.1 finetune sample to clear two Dependabot alerts (GHSA-mw35-8rx3-xf9r high RCE, GHSA-q5fh-2hc8-f6rq moderate DoS).Supersedes #14 (that branch was cut from a feature branch and dragged in unrelated files; this one is cut cleanly from master).