Stars
SGLang is a high-performance serving framework for large language models and multimodal models.
A Flexible Framework for Experiencing Heterogeneous LLM Inference/Fine-tune Optimizations
A PyTorch native library for training speculative decoding models
Engine-agnostic LLM gateway in Rust. Full OpenAI & Anthropic API compatibility across SGLang, vLLM, TRT-LLM, OpenAI, Gemini & more. Industry-first gRPC pipeline, KV cache-aware routing, chat histor…
Miles is an enterprise-facing reinforcement learning framework for LLM and VLM post-training, forked from and co-evolving with slime.
A visualized theorem prover based on Lean 4
Proof the completeness of Russel's Axiomatic System in lean4, and using C++ to automatically convert lean4 file to markdown file
Checkpoint-engine is a simple middleware to update model weights in LLM inference engines
A Distributed Attention Towards Linear Scalability for Ultra-Long Context, Heterogeneous Data Training
Supercharge Your LLM with the Fastest KV Cache Layer
I created a claude code deep researcher that seems to work better than the current deep research models
MoBA: Mixture of Block Attention for Long-Context LLMs
High-speed Large Language Model Serving for Local Deployment
Merico Build is a web app empowering open source developers, maintainers, and communities with metrics from Git, GitHub, and more.
CSI driver to bring SPDK to Kubernetes storage through NVMe-oF or iSCSI. Supports dynamic volume provisioning and enables Pods to use SPDK storage transparently.
A RocksDB compatible KV storage engine with better performance
Bot Framework provides the most comprehensive experience for building conversation applications.
A Python library for using the duoshuo API
A Python library for using the duoshuo API
PyCoder's Weekly Chinese Translate Sources Repo