latent.fs / tags / Benchmark — 12 items

/feed.xml

TAG

#Benchmark

2026-10 2 posts

  1. What Happens to HNSW Recall After Adding Vectors? (1M+1M)

    A 1M+1M insertion study in pgvector and Qdrant, comparing insertion order, batch boundaries, and fresh indexes. Segment telemetry and version-pinned code help explain their different behavior.

    DB

  2. What Happens to HNSW Recall After Adding Vectors? (10K+10K)

    A small pgvector and Qdrant experiment compares recall before and after vector insertion, then against fresh indexes over the same final data.

    DB

2026-09 2 posts

  1. Can tgrep, CodeGraph, Mantic, or ripwire Replace ripgrep?

    tgrep, CodeGraph, Mantic, and ripwire vs ripgrep on eight repos. Each hinges on a different variable: query, language coverage, file names, or phrasing.

    AI·Agent #35

  2. ego-browser and Aside Fail Differently

    Same missions, two browser agents: ego-browser isolates its tabs and returned success on missed clicks; Aside works in your real tabs and threw errors.

    AI·Agent #34

2026-06 1 post

  1. Speeding up LLM inference with MTP and diffusion

    Gemma 4 and Qwen 3.6 on one H100 at fp8: MTP ran 1.43–2.62x faster with GPQA accuracy effectively unchanged; diffusion was ~4x faster but less accurate.

    AI·Inference #31

2026-05 7 posts

  1. PG-Strom SSB Benchmark — Arrow FDW Comes Before GPU

    555 test cases on three servers: on heap storage PG-Strom's GPU gave 1.6x and lost to CPU on wide tables; with Arrow FDW it hit 10x at SF=100.

    DB #22

  2. GraphDB Benchmark (2/2) — Workload Matrix and Final Recommendations

    Eight graph engines on OLTP, memory, analytics, and differentiation queries, with a decision table by workload. On OLTP, RCTE tied MemGraph at 22.5K RPS.

    AI·RAG #21

  3. PDF to Markdown — Five Tools Compared

    Five PDF-to-Markdown converters on one academic paper, 100-point rubric: mineru scored 92 with formulas and tables intact; markitdown scored 14.

    AI·RAG #17

  4. Apple Silicon LLM Inference — Five Backends Compared

    Qwen3.5-9B on MLX, llama.cpp, Ollama, omlx, and vLLM Metal. MLX led single requests at 25 tok/s; only omlx batched concurrent requests.

    AI·Infra #13

  5. LightRAG Without Apache AGE — Graph Storage in Recursive CTE

    Implementing LightRAG's BaseGraphStorage on plain PostgreSQL with RCTE — why a 1-hop-dominant retrieval pattern fits flat SQL

    AI·RAG #14

  6. Long-Context Evaluation — NIAH and Lost in the Middle

    NIAH limits, the Lost in the Middle effect, alternative benchmarks, and measured recall across four reasoning-effort modes

    AI·Model #10

  7. GraphDB Benchmark, Eight Engines (Part 1) — Decomposing the RCTE 290x Gap

    On a 1.14M-edge knowledge graph, PostgreSQL RCTE had 290x the throughput of Apache AGE, traced to a ~13ms cypher() wrapper cost and plan generation.

    AI·RAG #20

TAGS 190

All 190 tags →