Dan-wanna-M / kbnfLinks
A high-performance constrained decoding engine based on context free grammar in Rust
☆55Updated 5 months ago
Alternatives and similar repositories for kbnf
Users that are interested in kbnf are comparing it to the libraries listed below
Sorting:
- Faster structured generation☆254Updated last week
- ☆58Updated 2 years ago
- Fast serverless LLM inference, in Rust.☆94Updated 7 months ago
- Experimental compiler for deep learning models☆67Updated last month
- This repository has code for fine-tuning LLMs with GRPO specifically for Rust Programming using cargo as feedback☆107Updated 7 months ago
- Inference Llama 2 in one file of zero-dependency, zero-unsafe Rust☆39Updated 2 years ago
- implement llava using candle☆15Updated last year
- ☆36Updated 11 months ago
- ☆134Updated last year
- High-performance MinHash implementation in Rust with Python bindings for efficient similarity estimation and deduplication of large datas…☆210Updated 3 weeks ago
- Modular Rust transformer/LLM library using Candle☆36Updated last year
- ☆19Updated last year
- Inference engine for GLiNER models, in Rust☆74Updated this week
- TensorRT-LLM server with Structured Outputs (JSON) built with Rust☆59Updated 6 months ago
- Low rank adaptation (LoRA) for Candle.☆162Updated 6 months ago
- A collection of optimisers for use with candle☆43Updated 2 months ago
- GPU based FFT written in Rust and CubeCL☆24Updated 4 months ago
- Locality Sensitive Hashing☆73Updated 2 years ago
- Efficent platform for inference and serving local LLMs including an OpenAI compatible API server.☆496Updated this week
- Fast and versatile tokenizer for language models, compatible with SentencePiece, Tokenizers, Tiktoken and more. Supports BPE, Unigram and…☆35Updated 2 weeks ago
- Automatically derive Python dunder methods for your Rust code☆20Updated 6 months ago
- Formatron empowers everyone to control the format of language models' output with minimal overhead.☆226Updated 4 months ago
- Structured outputs for LLMs☆52Updated last year
- ☆24Updated 6 months ago
- Andrej Karpathy's Let's build GPT: from scratch video & notebook implemented in Rust + candle☆77Updated last year
- A simple, CUDA or CPU powered, library for creating vector embeddings using Candle and models from Hugging Face☆45Updated last year
- Dataflow is a data processing library, primarily for machine learning.☆24Updated 2 years ago
- ☆12Updated 8 months ago
- Inference Llama 2 in one file of pure Rust 🦀☆233Updated 2 years ago
- ☆139Updated last year