feat(constants): add llm-d-vllm framework label#524
Open
ezrasilvera wants to merge 1 commit into
Open
Conversation
Register the llm-d-vllm framework in FW_REGISTRY with display label "llm-d vLLM" so the InferenceX GB200 DeepSeek-V4-Pro disaggregated benchmark series is recognized as a canonical framework (FRAMEWORK_KEYS) and rendered with a proper label instead of the uppercased slug. Add a matching FRAMEWORK_LABELS assertion. Signed-off-by: Ezra Silvera <ezra@il.ibm.com>
|
@ezrasilvera is attempting to deploy a commit to the SemiAnalysisAI Team on Vercel. A member of the Team first needs to authorize it. |
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
What
Registers a new framework
llm-d-vllminFW_REGISTRY(packages/constants) with the display label "llm-d vLLM".Why
We are adding llm-d (vLLM) as a new benchmark framework in the InferenceX benchmark framework - GB200 DeepSeek-V4-Pro FP4 P/D-disaggregated recipes (mid-curve 1P1D at conc 256/512/1024 and high-tpt 2P1D at conc 4096). Once those
sweeps ingest, the result rows carry
framework: llm-d-vllm.Without this entry the dashboard would not treat it as a canonical framework (
FRAMEWORK_KEYSis derived fromFW_REGISTRY) and would render the series with the uppercased slug "LLM-D-VLLM" instead of "llm-d vLLM".Change
packages/constants/src/framework-aliases.ts: add'llm-d-vllm': { label: 'llm-d vLLM' }toFW_REGISTRY(placedalphabetically, after
dynamo-vllm).packages/constants/src/framework-aliases.test.ts: add a matchingFRAMEWORK_LABELSassertion for the new label.Note
Low Risk
Constants-only registry and test change with no auth, data, or runtime logic changes.
Overview
Registers
llm-d-vllminFW_REGISTRYwith display label "llm-d vLLM", so upcoming benchmark rows using that framework key are treated as canonical and show the intended name in charts and tooltips instead of an uppercased slug.Because
FRAMEWORK_KEYSandFRAMEWORK_LABELSare derived from the registry, no other wiring is required. AFRAMEWORK_LABELSunit test covers the new entry.Reviewed by Cursor Bugbot for commit c11f50c. Bugbot is set up for automated code reviews on this repo. Configure here.