| | Training SID-1 to beat GPT-5 at search with 1k+ QPS RL (turbopuffer.com) |
| 12 points by maxrumpf 9 days ago | past | discuss |
|
| | Mixing numeric attributes into text search for better first-stage relevance (turbopuffer.com) |
| 3 points by _peregrine_ 33 days ago | past |
|
| | Rust zero-cost abstractions vs. SIMD (turbopuffer.com) |
| 2 points by whiteros_e 87 days ago | past |
|
| | Rust zero-cost abstractions vs. SIMD (turbopuffer.com) |
| 24 points by Sirupsen 87 days ago | past | 4 comments |
|
| | A distributed queue in a single JSON file on object storage (turbopuffer.com) |
| 171 points by Sirupsen 3 months ago | past | 55 comments |
|
| | How to build a distributed queue in a single JSON file on object storage (turbopuffer.com) |
| 2 points by _peregrine_ 3 months ago | past |
|
| | How to build a distributed queue in a single JSON file on object storage (turbopuffer.com) |
| 8 points by emschwartz 3 months ago | past | 1 comment |
|
| | Vectorized MAXSCORE over WAND, especially for long LLM-generated queries (turbopuffer.com) |
| 1 point by vismit2000 4 months ago | past |
|
| | ANN v3: 200ms p99 query latency over 100B vectors (turbopuffer.com) |
| 1 point by pbardea 4 months ago | past |
|
| | ANN v3: 200ms p99 query latency over 100B vectors (turbopuffer.com) |
| 2 points by jascha_eng 4 months ago | past |
|
| | ANN v3: 200ms p99 query latency over 100B vectors (turbopuffer.com) |
| 2 points by jascha_eng 4 months ago | past |
|
| | ANN v3: 200ms p99 query latency over 100B vectors (turbopuffer.com) |
| 4 points by tanelpoder 4 months ago | past | 1 comment |
|
| | Turbopuffer: Fast Search on Object Storage (turbopuffer.com) |
| 1 point by gk1 4 months ago | past |
|
| | ANN v3: 200ms p99 query latency over 100B vectors (turbopuffer.com) |
| 109 points by _peregrine_ 4 months ago | past | 47 comments |
|
| | Designing inverted indexes in a KV-store on object storage (turbopuffer.com) |
| 3 points by _peregrine_ 4 months ago | past |
|
| | Why BM25 queries with more terms can be faster (and other scaling surprises) (turbopuffer.com) |
| 53 points by _peregrine_ 4 months ago | past | 1 comment |
|
| | Vectorized MAXSCORE over WAND, especially for long LLM-generated queries (turbopuffer.com) |
| 4 points by Sirupsen 5 months ago | past |
|
| | Vectorized MAXSCORE over WAND, especially for long LLM-generated queries (turbopuffer.com) |
| 2 points by _peregrine_ 5 months ago | past |
|
| | Turbopuffer is now generally available (turbopuffer.com) |
| 1 point by tiagofneto on May 16, 2025 | past |
|
| | Native filtering for high-recall vector search (turbopuffer.com) |
| 2 points by softwaredoug on April 14, 2025 | past |
|
| | Turbopuffer: Continuous Recall Measurement (turbopuffer.com) |
| 6 points by MorganGallant on Sept 4, 2024 | past |
|
| | Turbopuffer: Fast search on object storage (turbopuffer.com) |
| 379 points by Sirupsen on July 9, 2024 | past | 64 comments |
|
| | Turbopuffer: Fast Search on Object Storage (turbopuffer.com) |
| 2 points by nalgeon on July 7, 2024 | past |
|
| | Turbopuffer: $1/month per million vectors (turbopuffer.com) |
| 46 points by georgehill on Oct 18, 2023 | past | 8 comments |
|
| | A Serverless Vector Database (turbopuffer.com) |
| 10 points by sorenbs on Oct 4, 2023 | past |
|
