--- title: "Reconstructed Slides: The Small Model Infrastructure Nobody Built (So We Did) — Filip Makraduli, Superlinked" category: "slides" video_id: "qdh_x-uRs9g" sourceLabels: ["Cropped public YouTube video frames", "Local OpenCV slide-region detection", "Local RapidOCR"] --- # Reconstructed Slides: The Small Model Infrastructure Nobody Built (So We Did) — Filip Makraduli, Superlinked ## Source Video [The Small Model Infrastructure Nobody Built (So We Did) — Filip Makraduli, Superlinked](https://www.youtube.com/watch?v=qdh_x-uRs9g) ## Method This deck is reconstructed from the existing video frame captures by detecting likely slide regions with OpenCV, cropping/upscaling those regions, deduplicating similar crops, and OCRing the cropped slide images locally. It is a cleaner companion to the full-stage frame deck. ## Reconstructed Slides ![[assets/reconstructed-slides/qdh_x-uRs9g/slide-003.jpg]] - Recreated text/layout view: [open HTML recreation](/assets/slide-recreations/reconstructed/qdh_x-uRs9g/slide-003.html) - AI slide classifier: `content_slide` confidence `0.95` - Text source: advanced OCR `rapidocr-live/left-72/contrast`. - OCR decision: ready — Small embedded article screenshot and composite slide elements are better suited for OCR than direct transcription. Slide text: > AIE AWRTERSDIAAYONA What Actually Makes Embedding > ★ ★ ★ ★ ★ Model InferenceFast? > From Fiash Artention to Quintzatoo,whero is the intergnce borteneck? Is it the architecturo, the mathis,or will wniting ovorything in Rust sohve olmy probiems？hdint: > R's Not Rust) > FIUPVAKRADUUI > N22,2V26 > Google Dee > AlEngineer ![[assets/reconstructed-slides/qdh_x-uRs9g/slide-004.jpg]] - Recreated text/layout view: [open HTML recreation](/assets/slide-recreations/reconstructed/qdh_x-uRs9g/slide-004.html) - AI slide classifier: `content_slide` confidence `0.97` - Text source: agent_vision. Slide text: > I realised ... I had to learn ![[assets/reconstructed-slides/qdh_x-uRs9g/slide-005.jpg]] - Recreated text/layout view: [open HTML recreation](/assets/slide-recreations/reconstructed/qdh_x-uRs9g/slide-005.html) - AI slide classifier: `content_slide` confidence `0.98` - Text source: agent_vision. Slide text: > LEARNING FROM FIRST PRINCIPLES > I knew models well > Training & fine-tuning > Evaluation & benchmarking > Applied AI research > vLLM, Flash Attention > I had overlooked infrastructure > How models run in production > GPU utilization & scheduling > Routing & autoscaling > Deployment & operations > Best way to learn? > Join the team building it. ![[assets/reconstructed-slides/qdh_x-uRs9g/slide-006.jpg]] - Recreated text/layout view: [open HTML recreation](/assets/slide-recreations/reconstructed/qdh_x-uRs9g/slide-006.html) - AI slide classifier: `content_slide` confidence `0.96` - Text source: advanced OCR `rapidocr-live/border-trim/contrast`. - OCR decision: ready — Contains a product screenshot with small text plus multiple embedded labels that are better handled by OCR. Slide text: > SoIjoined theworld class infrastructure team at: > Superlinked github.com/superlinked/sie > AIE VC - backed Al infrastructure company building the model stack for Al search and document processing > Workswithyourfavorite tools > P：Lanceoe OOC 电adamt WWeovoN > erginoering simcle.SIEadcs nstructon-folowng rerankors souopepna dueuogeupue modalraning dacasets and wSEyoucan so-host nfeence for M me reqsred deta transformucior' 'Lenceoe ceotralizes muit- scorng feorrg and ranking host bhem al in one chste comoose the best ndeing modes Weh SE you cen ser- 'Mooern serch sytems uniccis nacural language pre-procnss your outny ag soarchandwnSIEyoucan "Weviee's Query Agene > 011022 ceng See AnoeTanycei lco Van Lo C40400-5 > AI Engineer > AlEngineer EUROPE ![[assets/reconstructed-slides/qdh_x-uRs9g/slide-007.jpg]] - Recreated text/layout view: [open HTML recreation](/assets/slide-recreations/reconstructed/qdh_x-uRs9g/slide-007.html) - AI slide classifier: `content_slide` confidence `0.99` - Text source: advanced OCR `rapidocr-live/bright-screen/opencv-adaptive`. - OCR decision: ready — Dense chart and multi-column card slide with small text Slide text: > Performance dogrades as context flls up. More tokens,worse answers. Contextrofisrea! Manoges what goes INTO context. Context management > ★ ★? AIE ★ Tool calling Emboddings; reranking, extroction > CWhy not Just Opus 4.6?n > Works untif contoxt rot kils guolity > Sourco:Chromo Rosqorch > AlEngineer > AlEngineor EUROPE > hcn ![[assets/reconstructed-slides/qdh_x-uRs9g/slide-008.jpg]] - Recreated text/layout view: [open HTML recreation](/assets/slide-recreations/reconstructed/qdh_x-uRs9g/slide-008.html) - AI slide classifier: `content_slide` confidence `0.99` - Text source: advanced OCR `rapidocr-live/border-trim/contrast`. - OCR decision: ready — Diagram, small labels, and multiple text panels Slide text: > WHYITMATTERSFORYOURAGENTS > Taxonomy classification 10K categories Shopify product catalogue text + images A production story for tool calling Manages what goes INTO context, Context management > AIE title+image Product sio.extract() sie.encode() NU dosicoton emnbedrot- WSOL Electronics Computers,Laptops Tool calling Embeddings:reranking,extraction > sie.score() roronkcordoates > Switching model type = changing one parameter, not rebuilding infra "Why not just Opus 4.6?" Works until context rot kills quality > Engineering the future of Al > Al Enginecr ![[assets/reconstructed-slides/qdh_x-uRs9g/slide-009.jpg]] - Recreated text/layout view: [open HTML recreation](/assets/slide-recreations/reconstructed/qdh_x-uRs9g/slide-009.html) - AI slide classifier: `content_slide` confidence `0.98` - Text source: advanced OCR `rapidocr-live/center-82/opencv-adaptive`. - OCR decision: ready — Chart with small axes and labels Slide text: > YIN - MODEL SUPPORTIS KEY, OPEN SOURCEIS NOT STOPPINg > Modcl Pcrformancc vs sizc > AIE ★ > ★ > 3:0 > Gommo 4 modol porformonco =your infra noods to koepup > AlEngineer > AEnginccy EUROPE ![[assets/reconstructed-slides/qdh_x-uRs9g/slide-010.jpg]] - Recreated text/layout view: [open HTML recreation](/assets/slide-recreations/reconstructed/qdh_x-uRs9g/slide-010.html) - AI slide classifier: `content_slide` confidence `0.99` - Text source: none. - OCR decision: ready — Architecture matrix and side notes with small text ![[assets/reconstructed-slides/qdh_x-uRs9g/slide-011.jpg]] - Recreated text/layout view: [open HTML recreation](/assets/slide-recreations/reconstructed/qdh_x-uRs9g/slide-011.html) - AI slide classifier: `content_slide` confidence `0.99` - Text source: advanced OCR `rapidocr-live/border-trim/contrast`. - OCR decision: ready — Comparison table with many small cells Slide text: > SAME5STEPS,DIFFERENTIMPLEMENTATION > BERT Qwen2 CoLBERT > 1. Norm Post-norm(after) Pre-norm RMSNorm From base arch > 2. Q/K/V 3 → we fuse into 1 Separate (GQA) From base arch > AIE > 3. Position Absolute lookup RoPE rotation From base arch > 4. Attention MHA,allsame GQA (fewer KV) Bidirectioncl > 5. Output 1pooledvector 1pooledvector Nvectors(per-token) > Different fromBERT-differentforward pass Differentoutput type entirely > All on packed sequences with flash_attn_varlen = zero padding waste > Engineering the future of Al > AlEnginecr ![[assets/reconstructed-slides/qdh_x-uRs9g/slide-012.jpg]] - Recreated text/layout view: [open HTML recreation](/assets/slide-recreations/reconstructed/qdh_x-uRs9g/slide-012.html) - AI slide classifier: `content_slide` confidence `0.99` - Text source: advanced OCR `rapidocr-live/center-82/contrast`. - OCR decision: ready — Dense promo slide with QR code and small text Slide text: > ILEARNEDMYLESSON ON INFERENCE > We open sourced both the yin (model inference) and the yang (clust > Superlinked > AIE SlE - Superlinked Inference Engine > Dn-scurce dprioxctiencusterererbedsings,rerankirg.ngertrkscn > B.modelyFrreglrctiors.Frem iactcploDibernetes.AlAeache2.o > github.com/superlinked/sie > Google DeepMind > AlEnginecr ### Hidden Non-Slide Evidence - [`slide-001.jpg`](/assets/reconstructed-slides/qdh_x-uRs9g/slide-001.jpg) — `sponsor_logo` confidence `0.99`; sponsor logo wall - [`slide-002.jpg`](/assets/reconstructed-slides/qdh_x-uRs9g/slide-002.jpg) — `speaker_stage` confidence `0.98`; camera shot of speaker on stage with projected slide, not a clean presentation slide Classification audit: `raw/sources/slide-ai-classification/reconstructed/qdh_x-uRs9g/audit.json`