Dan-wanna-M / kbnfLinks
A high-performance constrained decoding engine based on context free grammar in Rust
☆53Updated last month
Alternatives and similar repositories for kbnf
Users that are interested in kbnf are comparing it to the libraries listed below
Sorting:
- This repository has code for fine-tuning LLMs with GRPO specifically for Rust Programming using cargo as feedback☆95Updated 3 months ago
- implement llava using candle☆15Updated last year
- ☆20Updated 8 months ago
- High-performance MinHash implementation in Rust with Python bindings for efficient similarity estimation and deduplication of large datas…☆177Updated this week
- ☆30Updated 7 months ago
- Experimental compiler for deep learning models☆67Updated last month
- Fast serverless LLM inference, in Rust.☆76Updated 3 months ago
- Inference engine for GLiNER models, in Rust☆59Updated 2 months ago
- ☆130Updated last year
- Inference Llama 2 in one file of zero-dependency, zero-unsafe Rust☆38Updated last year
- GPU based FFT written in Rust and CubeCL☆23Updated 2 weeks ago
- ☆58Updated 2 years ago
- TensorRT-LLM server with Structured Outputs (JSON) built with Rust☆55Updated last month
- 8-bit floating point types for Rust☆46Updated 3 months ago
- Faster structured generation☆224Updated last month
- Modular Rust transformer/LLM library using Candle☆36Updated last year
- ☆11Updated 4 months ago
- An extension library to Candle that provides PyTorch functions not currently available in Candle☆39Updated last year
- 👷 Build compute kernels☆68Updated this week
- Fast and versatile tokenizer for language models, compatible with SentencePiece, Tokenizers, Tiktoken and more. Supports BPE, Unigram and…☆26Updated 3 months ago
- ☆12Updated last year
- A collection of optimisers for use with candle☆36Updated last month
- Tensor library for Zig☆11Updated 7 months ago
- Locality Sensitive Hashing☆72Updated last year
- Graph model execution API for Candle☆13Updated 7 months ago
- Low rank adaptation (LoRA) for Candle.☆150Updated 2 months ago
- A simple, CUDA or CPU powered, library for creating vector embeddings using Candle and models from Hugging Face☆37Updated last year
- ☆23Updated 2 months ago
- Efficent platform for inference and serving local LLMs including an OpenAI compatible API server.☆380Updated this week
- Structured outputs for LLMs☆47Updated 11 months ago