compound-ai-systems / awesome-compound-ai-systems
A curated list of awesome Compound AI Systems
☆22Updated 3 months ago
Related projects: ⓘ
- Pretrain, finetune and serve LLMs on Intel platforms with Ray☆95Updated this week
- The code for the paper ROUTERBENCH: A Benchmark for Multi-LLM Routing System☆86Updated 3 months ago
- ☆15Updated 3 months ago
- Tune efficiently any LLM model from HuggingFace using distributed training (multiple GPU) and DeepSpeed. Uses Ray AIR to orchestrate the …☆50Updated last year
- ☆27Updated last month
- Framework for building data agent workflows☆70Updated last month
- End-to-End LLM Guide☆91Updated 2 months ago
- A simple service that integrates vLLM with Ray Serve for fast and scalable LLM serving.☆45Updated 5 months ago
- LLM Serving Performance Evaluation Harness☆45Updated 3 weeks ago
- ☆42Updated this week
- ☆77Updated this week
- IBM development fork of https://github.com/huggingface/text-generation-inference☆52Updated this week
- Modular and structured prompt caching for low-latency LLM inference☆43Updated 4 months ago
- Evaluation and analysis code for LLM360☆75Updated 3 months ago
- DSPY on action with OpenSource LLMs.☆49Updated 5 months ago
- Benchmark baseline for retrieval qa applications☆90Updated 5 months ago
- Using LlamaIndex with Ray for productionizing LLM applications☆70Updated last year
- Self-host LLMs with vLLM and BentoML☆62Updated this week
- ☆15Updated last year
- ☆83Updated 11 months ago
- experiments with inference on llama☆106Updated 3 months ago
- Formal-LLM: Integrating Formal Language and Natural Language for Controllable LLM-based Agents☆102Updated 3 months ago
- WIP. Veloce is a low-code Ray-based parallelization library that makes machine learning computation novel, efficient, and heterogeneous.☆18Updated 2 years ago
- Examples on how to use LangChain and Ray☆217Updated last year
- Deploy and Scale LLM-based applications☆26Updated last year
- Open source project for data preparation of LLM application builders☆124Updated this week
- A collection of all available inference solutions for the LLMs☆65Updated 3 weeks ago
- ☆71Updated 3 months ago
- Evaluation of bm42 sparse indexing algorithm☆60Updated 2 months ago
- Three examples of recommendation system pipelines with NVIDIA Merlin and Redis☆56Updated last year