Sun, Jun 28, 2026

baidu/Unlimited-OCR (paper) parses dozens of pages in one forward pass by fixing the real bottleneck in end-to-end OCR.

• The problem: an OCR decoder types out the page token-by-token, and its KV cache grows unbounded with output length — so memory climbs and speed decays the longer the doc, forcing page-by-page loops that wipe memory each step.
• The trick (Reference Sliding Window Attention): split context into two zones with different retention. Vision/prompt tokens stay fully visible and pinned forever (the “source book”); each token attends to only the last 128 of its own outputs (the “last few words you wrote”). KV cache becomes a fixed-size queue, so memory and TPS stay flat regardless of output length.
• The non-obvious part: discarding history improves accuracy (+6% on OmniDocBench, beating Qwen2.5-VL-72B at 3B/0.5B-active) — full attention can diverge on long dense output, and pinned vision tokens never blur.
• Cheap to build: freeze DeepSeek-OCR’s encoder, fine-tune only the decoder with the swapped attention.
• Generalizes past OCR: separate what you reference from what you remember.
• Ran it on an M1 Mac (32GB) with R-SWA intact, no NVIDIA. The official HF model (trust_remote_code) already ships R-SWA as a pure-PyTorch eager ring buffer (SlidingWindowLlamaAttention, picked via attn_implementation="eager") — not buried in a CUDA/FlashAttention kernel. So the “port” was just stripping .cuda()/torch.autocast("cuda") and running bf16 on MPS; zero MPS op-gaps hit. bf16 works on MPS in torch 2.12.
• Proof R-SWA is live: instrument the KV cache during decode — on a 540-token page it plateaus at prefill(277) + window(128) = 405 and never grows (full MHA would hit 817). That constant-cache assertion + Distinct-35≈1.0 are the decisive signals, not edit distance (too noisy vs a single reference).
• Gotcha: feeding all pages to one generate() (infer_multi) loops at the document level — the 128-token decode window forgets the doc was already transcribed while the vision prefix still shows every page, so it restarts from page 1. Fix = one generate() per page (matches official infer.py PAGE_SIZE=1). Accuracy then lands at/below gemini-vs-docai inter-annotator noise (~0.31 mean edit). ~35–55 s/page on M1.

Many asymmetric embedding models need task prefixes on inputs, and skipping them quietly degrades relevance. Each model has its own scheme: nomic (search_query:/search_document:), E5 (query:/passage:), BGE (a query instruction sentence, bare docs) — not interchangeable. OpenAI text-embedding-3-* and all-MiniLM-L6-v2 need none. Whether you add the prefix depends on the serving layer, not the model: raw endpoints (llama.cpp /v1/embeddings, HF TEI, Ollama) send bare text so it’s on you, while sentence-transformers (prompt_name="query") and vendor SDKs inject it for you. Adding search_query:/search_document: to a nomic-v1.5 call lifted cosine similarity on a real query/doc pair from 0.54 to 0.60 at zero cost.

Vim motion tips for Zed. Turn on relative line numbers, and let vim mode switch them to absolute in Insert mode, so you get jump distances in Normal mode and context while typing.

{ "relative_line_numbers": true, "vim": { "toggle_relative_line_numbers": true } }

• [[ / ]] jump between function definitions in a large Django or FastAPI file.
• f: moves to the end of an if, def or class line.

Zed’s Hidden Gems: Community Edition thread collects users’ favourite Zed features and workflows, a companion to Hidden Gems: Team Edition. One tip from it: point agent.commit_message_model at gemini-2.0-flash on a free Gemini API key to write commit messages.