guidance-ai / llguidance
Super-fast Structured Outputs
☆136Updated this week
Alternatives and similar repositories for llguidance:
Users that are interested in llguidance are comparing it to the libraries listed below
- Faster structured generation☆189Updated this week
- TensorRT-LLM server with Structured Outputs (JSON) built with Rust☆41Updated this week
- The Batched API provides a flexible and efficient way to process multiple requests in a batch, with a primary focus on dynamic batching o…☆124Updated 2 months ago
- A high-performance constrained decoding engine based on context free grammar in Rust☆47Updated 2 months ago
- ☆125Updated 10 months ago
- Formatron empowers everyone to control the format of language models' output with minimal overhead.☆189Updated 2 months ago
- An efficent implementation of the method proposed in "The Era of 1-bit LLMs"☆154Updated 4 months ago
- 🕹️ Performance Comparison of MLOps Engines, Frameworks, and Languages on Mainstream AI Models.☆136Updated 7 months ago
- Fast parallel LLM inference for MLX☆173Updated 8 months ago
- Comparison of Language Model Inference Engines☆207Updated 2 months ago
- An easy-to-understand framework for LLM samplers that rewind and revise generated tokens☆135Updated 3 weeks ago
- ☆199Updated last year
- ☆149Updated 3 months ago
- Manage scalable open LLM inference endpoints in Slurm clusters☆253Updated 8 months ago
- Long context evaluation for large language models☆201Updated last week
- Baguetter is a flexible, efficient, and hackable search engine library implemented in Python. It's designed for quickly benchmarking, imp…☆171Updated 6 months ago
- minimal pytorch implementation of bm25 (with sparse tensors)☆97Updated last year
- ☆113Updated 5 months ago
- Efficent platform for inference and serving local LLMs including an OpenAI compatible API server.☆324Updated this week
- Late Interaction Models Training & Retrieval☆254Updated this week
- Code for the paper "QMoE: Practical Sub-1-Bit Compression of Trillion-Parameter Models".☆270Updated last year
- Q-GaLore: Quantized GaLore with INT4 Projection and Layer-Adaptive Low-Rank Gradients.☆196Updated 7 months ago
- Experiments on speculative sampling with Llama models☆125Updated last year
- experiments with inference on llama☆104Updated 9 months ago
- Cold Compress is a hackable, lightweight, and open-source toolkit for creating and benchmarking cache compression methods built on top of…☆121Updated 7 months ago
- an implementation of Self-Extend, to expand the context window via grouped attention☆118Updated last year