mixedbread-ai / batchedLinks
The Batched API provides a flexible and efficient way to process multiple requests in a batch, with a primary focus on dynamic batching of inference workloads.
☆147Updated 2 months ago
Alternatives and similar repositories for batched
Users that are interested in batched are comparing it to the libraries listed below
Sorting:
- Baguetter is a flexible, efficient, and hackable search engine library implemented in Python. It's designed for quickly benchmarking, imp…☆189Updated last year
- High-Performance Engine for Multi-Vector Search☆155Updated this week
- minimal pytorch implementation of bm25 (with sparse tensors)☆104Updated last year
- Generalist and Lightweight Model for Text Classification☆156Updated 3 months ago
- ☆155Updated 9 months ago
- Late Interaction Models Training & Retrieval☆576Updated this week
- ☆69Updated 2 months ago
- FastFit ⚡ When LLMs are Unfit Use FastFit ⚡ Fast and Effective Text Classification with Many Classes☆212Updated 4 months ago
- ☆40Updated 2 months ago
- Crispy reranking models by Mixedbread☆35Updated 2 months ago
- ☆210Updated 2 months ago
- ☆199Updated last year
- Notebooks for training universal 0-shot classifiers on many different tasks☆136Updated 8 months ago
- Simple UI for debugging correlations of text embeddings☆290Updated 3 months ago
- Efficient vector database for hundred millions of embeddings.☆207Updated last year
- experiments with inference on llama☆104Updated last year
- ☆135Updated 3 weeks ago
- Pre-train Static Word Embeddings☆85Updated this week
- NLP with Rust for Python 🦀🐍☆64Updated 4 months ago
- A stable, fast and easy-to-use inference library with a focus on a sync-to-async API☆45Updated 11 months ago
- Trully flash implementation of DeBERTa disentangled attention mechanism.☆63Updated last week
- Python API for https://vespa.ai, the open big data serving engine☆139Updated last week
- Optimus is a flexible and scalable framework built to train language models efficiently across diverse hardware configurations, including…☆67Updated 2 months ago
- XTR/WARP (SIGIR'25) is an extremely fast and accurate retrieval engine based on Stanford's ColBERTv2/PLAID and Google DeepMind's XTR.☆163Updated 4 months ago
- code for training & evaluating Contextual Document Embedding models☆197Updated 4 months ago
- Lite weight wrapper for the independent implementation of SPLADE++ models for search & retrieval pipelines. Models and Library created by…☆32Updated last year
- ☆49Updated 7 months ago
- 🕹️ Performance Comparison of MLOps Engines, Frameworks, and Languages on Mainstream AI Models.☆137Updated last year
- A Python wrapper around HuggingFace's TGI (text-generation-inference) and TEI (text-embedding-inference) servers.☆33Updated 4 months ago
- ☆30Updated last year