--- title: 14× faster embeddings: how we rebuilt the ONNX path in... description: Manticore Search 27.1.5 ships a new ONNX Runtime backend for auto-embeddings that delivers ~14× faster throughput than the previous SentenceTransformers/Candle... canonical: https://daily.dev/posts/14-faster-embeddings-how-we-rebuilt-the-onnx-path-in-manticore-9ac8mmjgg twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: 14× faster embeddings: how we rebuilt the ONNX path in Manticore | daily.dev og:description: Manticore Search 27.1.5 ships a new ONNX Runtime backend for auto-embeddings that delivers ~14× faster throughput than the previous SentenceTransformers/Candle... og:url: https://daily.dev/posts/14-faster-embeddings-how-we-rebuilt-the-onnx-path-in-manticore-9ac8mmjgg og:image: https://api.daily.dev/og/posts/9AC8mMjGG.png og:image:alt: 14× faster embeddings: how we rebuilt the ONNX path in Manticore og:image:width: 1200 og:image:height: 630 og:locale: en --- > ## Documentation Index > Fetch the complete documentation index at: https://daily.dev/llms.txt > Use this file to discover all available pages before exploring further. # 14× faster embeddings: how we rebuilt the ONNX path in Manticore **[Manticore](https://daily.dev/sources/manticoresearch)** · 16 min read · 4 upvotes · 0 comments ## Summary Manticore Search 27.1.5 ships a new ONNX Runtime backend for auto-embeddings that delivers ~14× faster throughput than the previous SentenceTransformers/Candle path on CPU. The old path was stuck at 5–11 docs/sec regardless of concurrency or batch size; the new one reaches 70–233 docs/sec. Key engineering decisions: sharing a single ORT session across concurrent callers (safe on Linux/macOS per ORT's C API docs), processing one document per inference call instead of batching (padding overhead made batching slower with variable-length inputs), and disabling intra-op thread spinning to free CPU for the rest of the system. For maximum bulk ingest throughput, the recommended pattern is large batches (32–128 docs) from a single client thread, since ORT already parallelises internally. GPU support and Windows perf parity are planned for future releases. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Similar posts on daily.dev - [Manticore Search 13.11.0: Introducing Auto Embeddings and Enhanced AI Search](https://daily.dev/posts/manticore-search-13-11-0-introducing-auto-embeddings-and-enhanced-ai-search-vwbvt90ph) · Manticore · 1 upvotes · 0 comments --- Tags: [#rust](https://daily.dev/tags/rust), [#vector-search](https://daily.dev/tags/vector-search), [#embeddings](https://daily.dev/tags/embeddings), [#manticore-search](https://daily.dev/tags/manticore-search) [View this post on daily.dev](https://daily.dev/posts/14-faster-embeddings-how-we-rebuilt-the-onnx-path-in-manticore-9ac8mmjgg) ```json {"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]} {"@context":"https://schema.org","@type":"TechArticle","headline":"14× faster embeddings: how we rebuilt the ONNX path in Manticore","url":"https://daily.dev/posts/14-faster-embeddings-how-we-rebuilt-the-onnx-path-in-manticore-9ac8mmjgg","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/14-faster-embeddings-how-we-rebuilt-the-onnx-path-in-manticore-9ac8mmjgg"},"datePublished":"2026-07-09T07:50:01.916Z","dateModified":"2026-08-24T06:57:38.452Z","description":"Manticore Search 27.1.5 ships a new ONNX Runtime backend for auto-embeddings that delivers ~14× faster throughput than the previous SentenceTransformers/Candle...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/df2083cad551b512db37943e6b386478?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/df2083cad551b512db37943e6b386478?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"Manticore","inLanguage":"en","publisher":{"@type":"Organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180}},"author":{"@type":"Organization","name":"Manticore","logo":"https://media.daily.dev/image/upload/s--FP5Ea08h--/f_auto/v1754225081/logos/manticoresearch","url":"https://daily.dev/sources/manticoresearch"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/14-faster-embeddings-how-we-rebuilt-the-onnx-path-in-manticore-9ac8mmjgg","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":4},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"rust,vector-search,embeddings,manticore-search","timeRequired":"PT16M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"Manticore","item":"https://daily.dev/sources/manticoresearch"},{"@type":"ListItem","position":3,"name":"14× faster embeddings: how we rebuilt the ONNX path in Manticore"}]} ```