Stars
่ฐทๆญๆฐไนฆAgent่ฎพ่ฎกๆจกๅผ(agentic design patterns)ไธญๆ็๏ผๆ็ปญๆดๆฐใ้๏ผๅจ็บฟ้ ่ฏปใpdfๅepub็ตๅญไนฆไธ่ฝฝใ
Cost-efficient and pluggable Infrastructure components for GenAI inference
Efficient and easy multi-instance LLM serving
tiktoken is a fast BPE tokeniser for use with OpenAI's models.
Ongoing research training transformer models at scale
่ฏบไบ็ๅคๅคงๆจกๅ็ ๅ่ๅ็็ๆญฃ็ๅฟ้ ธไธ้ปๆ็ๆ ไบใ
่ฎจ่ดผ็ไบ้นคๆชๆ
๐ค Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.
Community maintained hardware plugin for vLLM on Ascend
A high-throughput and memory-efficient inference and serving engine for LLMs
Awesome-LLM-KV-Cache: A curated list of ๐Awesome LLM KV Cache Papers with Codes.
For developers, who are building real-time data-driven applications, Redis is the preferred, fastest, and most feature-rich cache, data structure server, and document and vector query engine.
A blazing fast and lightweight C asymmetric coroutine library ๐ โ ๐โ ๐
libco is a coroutine library which is widely used in wechat back-end service. It has been running on tens of thousands of machines since 2013.
An open sourced implementation of Bw-Tree in SQL Server Hekaton
An Implementation of Poptrie IP Routing Table Lookup Algorithm
The Moby Project - a collaborative project for the container ecosystem to assemble container-based systems
Unified Communication X (mailing list - https://elist.ornl.gov/mailman/listinfo/ucx-group)
A new data structure for accurate on-line accumulation of rank-based statistics such as quantiles and trimmed means