recipe(dell-research-harvard/names-linking-model): add verified CPU fp32/fp16 recipes - #1214
Open
codykk wants to merge 1 commit into
Open
recipe(dell-research-harvard/names-linking-model): add verified CPU fp32/fp16 recipes#1214codykk wants to merge 1 commit into
codykk wants to merge 1 commit into
Conversation
…-model Add CPU fp32 and fp16 recipes for the names-linking-model (MPNet architecture). Verified build, perf, and eval (cosine_spearman=81.54) on both precisions.
codykk
marked this pull request as ready for review
July 27, 2026 06:15
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
Add verified CPU (fp32/fp16) feature-extraction recipe for
dell-research-harvard/names-linking-model(MPNet architecture, sentence embeddings for entity name linking).Model metadata
feature-extraction(checkpoint, transformers, optimum-onnx, winml)Validation and support evidence
Baseline (origin/main @ d5f24d2, winml 0.2.0):
winml build -m dell-research-harvard/names-linking-model --ep cpu --device cpu→ ✅ Build complete in 42.2swinml perf→ ✅ 227.92ms avg, 4.39 samp/swinml eval --task feature-extraction→ ✅ cosine_spearman = 81.5376Goal: L3 (task metric) — baseline already at L3; contribution establishes verified
cpu/cpucoverage with recipes.Outcome: L0 — recipe-only (auto-config already correct; recipe captures verified EP/device/precision coverage).
Per-tuple results
Delta: Recipe identical to
winml configauto-output — filed for verifiedcpu/cpucoverage claim on both precisions.Reproduce commands