pixelspark / poly
A single-binary, GPU-accelerated LLM server (HTTP and WebSocket API) written in Rust
☆80Updated 9 months ago
Related projects ⓘ
Alternatives and complementary repositories for poly
- Low rank adaptation (LoRA) for Candle.☆127Updated 2 months ago
- A simple, CUDA or CPU powered, library for creating vector embeddings using Candle and models from Hugging Face☆26Updated 6 months ago
- llm_utils: Basic LLM tools, best practices, and minimal abstraction.☆35Updated 3 weeks ago
- The Easiest Rust Interface for Local LLMs and an Interface for Deterministic Signals from Probabilistic LLM Vibes☆131Updated 2 weeks ago
- Extract core logic from qdrant and make it available as a library.☆56Updated 7 months ago
- Andrej Karpathy's Let's build GPT: from scratch video & notebook implemented in Rust + candle☆59Updated 7 months ago
- Rust implementation of Surya☆50Updated last month
- An LLM interface (chat bot) implemented in pure Rust using HuggingFace/Candle over Axum Websockets, an SQLite Database, and a Leptos (Was…☆121Updated 3 weeks ago
- LLaMa 7b with CUDA acceleration implemented in rust. Minimal GPU memory needed!☆101Updated last year
- AI gateway and observability server written in Rust. Designed to help optimize multi-agent workflows.☆46Updated 4 months ago
- Library for doing RAG☆39Updated this week
- auto-rust is an experimental project that automatically generate Rust code with LLM (Large Language Models) during compilation, utilizing…☆31Updated 4 months ago
- Rust client for the huggingface hub aiming for minimal subset of features over `huggingface-hub` python package☆153Updated last month
- High-level, optionally asynchronous Rust bindings to llama.cpp☆176Updated 5 months ago
- Unofficial Rust bindings to Apple's mlx framework☆64Updated this week
- A Fish Speech implementation in Rust, with Candle.rs☆40Updated 3 weeks ago
- ☆155Updated this week
- Super-simple, fully Rust powered "memory" (doc store + semantic search) for LLM projects, semantic search, etc.☆55Updated last year
- A Rust implementation of OpenAI's Whisper model using the burn framework☆268Updated 6 months ago
- Neural search for web-sites, docs, articles - online!☆126Updated 2 weeks ago
- Efficent platform for inference and serving local LLMs including an OpenAI compatible API server.☆260Updated 2 weeks ago
- ☆22Updated last month
- Inference Llama 2 in one file of pure Rust 🦀☆228Updated last year
- An extension library to Candle that provides PyTorch functions not currently available in Candle☆36Updated 7 months ago
- High-performance MinHash implementation in Rust with Python bindings for efficient similarity estimation and deduplication of large datas…☆65Updated 3 months ago
- pgvector support for Rust☆119Updated 2 weeks ago
- 8-bit floating point types for Rust☆40Updated last month
- Implementing the BitNet model in Rust☆26Updated 6 months ago
- OpenAI compatible API for serving LLAMA-2 model☆215Updated last year
- LLM Orchestrator built in Rust☆263Updated 7 months ago