lightseq
llm-package
lightseq | llm-package | |
---|---|---|
1 | 1 | |
3,098 | 13 | |
0.9% | - | |
3.7 | 7.5 | |
12 months ago | 5 months ago | |
C++ | Starlark | |
GNU General Public License v3.0 or later | MIT License |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
lightseq
llm-package
-
One line local run to spin up model of your choice, parallel runs, chatbot UI and more!
Check it out here: https://github.com/kurtosis-tech/llm-package
What are some alternatives?
accelerate-kullback-liebler
text-generation-inference - Large Language Model Text Generation Inference
rust-bert - Rust native ready-to-use NLP pipelines and transformer-based models (BERT, DistilBERT, GPT2,...)
free-ai-chat-sites - 🤖 Several unofficial websites/mirrors for using "Closed"AI's Chat*** for free. We are not endorsing any of the listed services.
FasterTransformer - Transformer related optimization, including BERT, GPT
Roy - Roy: A lightweight, model-agnostic framework for crafting advanced multi-agent systems using large language models.
cuhnsw - CUDA implementation of Hierarchical Navigable Small World Graph algorithm
vllm - A high-throughput and memory-efficient inference and serving engine for LLMs
cuml - cuML - RAPIDS Machine Learning Library
AtomGPT - ä¸è‹±æ–‡é¢„è®ç»ƒå¤§æ¨¡åž‹ï¼Œç›®æ ‡ä¸ŽChatGPT的水平一致
instant-ngp - Instant neural graphics primitives: lightning fast NeRF and more
intel-extension-for-transformers - âš¡ Build your chatbot within minutes on your favorite device; offer SOTA compression techniques for LLMs; run LLMs efficiently on Intel Platformsâš¡